System, method, and computer program product for determining non-indexed record correspondence

Abstract

Systems, computer-implemented methods, and computer program products for determining non-indexed record correspondence are described herein. The methods can include receiving a clearing record comprising at least one key field, comparing a value associated with a first key field of the clearing record to values associated with first key fields of one or more authorization records associated with one or more payment transactions, and determining that the clearing record corresponds to an authorization record among the one or more authorization records based on comparing the value associated with the first key field of the clearing record to the values associated with the first key fields of the one or more authorization records. The methods also include generating an updated clearing record based on determining that the clearing record corresponds to the authorization record, and transmitting the updated clearing record.

Description

[0001] Cross-referencing related applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 952,950, filed December 23, 2019, the disclosure of which is hereby incorporated in its entirety by reference. Technical Field

[0003] This disclosure generally relates to determining the correspondence of non-indexed records, and in some non-limiting embodiments or aspects, to systems, methods, and computer program products for predicting that a liquidation record corresponds to an authorized record when the liquidation record is not identified as corresponding to an authorized record in an index. Background Technology

[0004] After an individual initiates and approves a payment transaction, the issuing institution involved in the payment transaction can generate and maintain an authorization record, which is then retained in the individual's account. The acquiring institution can transmit the clearing record associated with the payment transaction to complete the transaction. However, upon receipt, the issuing institution may not be able to accurately determine the authorization record corresponding to the clearing record. For example, in cases where the approved transaction amount specified in the authorization record does not match the final transaction amount specified in the clearing record (e.g., when a tip is added to the approved transaction amount after approval, when currency changes affect the final transaction amount, when the authorization record for the payment transaction is deleted from the database after a period of time (e.g., five days) to save database space), the issuing institution may not be able to accurately determine that the authorization record matches the clearing record. The issuing institution may then process the clearing record as a forced post-payment transaction (e.g., a payment transaction approved by the merchant system but without authorization from the issuing system involved in the payment transaction, such as by providing a previously obtained authorization code).

[0005] If a forced postpayment transaction is against a fraudulent payment transaction (e.g., a payment transaction initiated by an individual not authorized to use the payment device during this period), and / or if a forced postpayment transaction is against a previously unauthorized payment transaction (e.g., a payment transaction not pre-authorized by the issuer's system), the forced postpayment transaction may be subject to a chargeback. If the issuer cannot identify a match in the clearing record, the issuer may need to process the clearing record as a forced postpayment transaction, and if the forced postpayment transaction is fraudulent and / or unauthorized, a chargeback may be subsequently issued, allowing the use of other network resources.

[0006] There is a need in the art for improved systems and methods for identifying matches between clearing records and authorization records, including in cases where the clearing records do not correspond exactly to the authorization records. There is also a need in the art for improved systems and methods for accurately identifying clearing records as being associated with forced post payment transactions. SUMMARY

[0007] Accordingly, systems, methods, and computer program products for determining non-indexed record correspondence by determining whether a clearing record corresponds to an authorization record are disclosed.

[0008] According to some non-limiting embodiments or aspects, a computer-implemented method of determining non-indexed record correspondence is provided. The method can include receiving, by at least one processor, a clearing record comprising at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network. The method can also include comparing, by the at least one processor, a value associated with a first key field of the clearing record to a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records. The one or more authorization records can be associated with an authorization request for a payment transaction of the one or more payment transactions. The method can further include determining, by the at least one processor, that the clearing record corresponds to an authorization record among the one or more authorization records based on comparing the value associated with the first key field of the clearing record to the value associated with the first key field of the one or more authorization records. The method can further include generating, by the at least one processor, an updated clearing record based on determining that the clearing record corresponds to the authorization record. The method can further include transmitting, by the at least one processor, the updated clearing record.

[0009] In some non-limiting embodiments or aspects, receiving the clearing record associated with the one or more payment transactions can include receiving, by the at least one processor, a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions. The method can further include normalizing, by the at least one processor, one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with an issuer system. When normalizing the one or more clearing records of the clearing batch file, the at least one processor can convert one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0010] In some non-limiting embodiments or aspects, the method can include comparing, by the at least one processor, a value associated with a second key field of the clearing record and a value associated with a second key field of the one or more authorization records. The second key field of the clearing record can correspond to the second key field of the one or more authorization records. Determining that the clearing record corresponds to the authorization record among the one or more authorization records can include determining, by the at least one processor, that the clearing record corresponds to the authorization record among the one or more authorization records based on comparing the value associated with the second key field of the clearing record and the value associated with the second key field of the one or more authorization records. The first key field can be associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and the second key field can be associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0011] In some non-limiting embodiments or aspects, determining that the clearing record corresponds to the authorization record among the one or more authorization records can include determining, by the at least one processor, that the value associated with the first key field of the clearing record matches the value associated with the first key field of the authorization record. Determining that the clearing record corresponds to the authorization record among the one or more authorization records can also include determining, by the at least one processor, that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record. The method can further include determining, by the at least one processor, that the clearing record partially matches the authorization record based on determining that the value associated with the first key field of the clearing record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record.

[0012] In some non-limiting embodiments or aspects, determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining, by the at least one processor, that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record. Determining that the settlement record corresponds to the authorization record among the one or more authorization records can further include determining, by the at least one processor, that the value associated with the second key field of the settlement record matches the value associated with the second key field of the authorization record. The method can further include determining, by the at least one processor, that the settlement record matches the authorization record based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record matches the value associated with the second key field of the authorization record.

[0013] In some non-limiting embodiments or aspects, determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining, by the at least one processor, that the value associated with the first key field of the settlement record does not match the value associated with the first key field of the authorization record. Determining that the settlement record corresponds to the authorization record among the one or more authorization records can further include determining, by the at least one processor, that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record. The method can further include determining, by the at least one processor, that the settlement record does not match the authorization record based on determining that the value associated with the first key field of the settlement record does not match the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record.

[0014] In some non-limiting embodiments or aspects, generating the updated settlement record can include providing, by the at least one processor, the settlement record and the authorization record as input to a machine learning model and generating, by the at least one processor, a prediction associated with a confidence score that the settlement record matches the authorization record based on providing the settlement record and the authorization record as the input to the machine learning model. Generating the updated settlement record can further include updating, by the at least one processor, the settlement record based on the confidence score.

[0015] In some non-limiting embodiments or aspects, updating the clearing record based on the confidence score can include at least one of: (i) appending, by the at least one processor, the confidence score to the clearing record; (ii) appending, by the at least one processor, an initial transaction amount of the authorization record to the clearing record; and (iii) appending, by the at least one processor, a transaction identifier of the authorization record to the clearing record.

[0016] In some non-limiting embodiments or aspects, the method can include generating, by the at least one processor, an updated clearing batch file based on the clearing batch file and the updated clearing record. Transmitting the updated clearing record can include transmitting, by the at least one processor, the updated clearing batch file to an issuer system.

[0017] In some non-limiting embodiments or aspects, generating the updated clearing record based on determining that the clearing record corresponds to the authorization record can include: providing, by the at least one processor, the clearing record and the one or more authorization records to a machine learning model; and generating, by the at least one processor, a prediction associated with a merchant transaction pattern and a confidence score based on providing the clearing record and the one or more authorization records to the machine learning model. Generating the updated clearing record based on determining that the clearing record corresponds to the authorization record can also include updating, by the at least one processor, the clearing record based on the merchant transaction pattern and the confidence score.

[0018] According to some non-limiting embodiments or aspects, a system for determining non-indexed record correspondence is provided. The system can include a server comprising at least one processor. The at least one processor can be programmed and / or configured to receive a clearing record comprising at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network. The at least one processor can be programmed and / or configured to compare a value associated with a first key field of the clearing record to a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records. The one or more authorization records can be associated with an authorization request for a payment transaction of the one or more payment transactions. The at least one processor can be programmed and / or configured to determine that the clearing record corresponds to an authorization record among the one or more authorization records based on comparing the value associated with the first key field of the clearing record to the value associated with the first key field of the one or more authorization records. The at least one processor can be programmed and / or configured to generate an updated clearing record based on determining that the clearing record corresponds to the authorization record. The at least one processor can be programmed and / or configured to transmit the updated clearing record.

[0019] In some non-limiting embodiments or aspects, receiving the clearing record associated with the one or more payment transactions can include receiving a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions. The at least one processor can be further programmed and / or configured to normalize one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with an issuer system. When normalizing the one or more clearing records of the clearing batch file, the at least one processor can convert one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0020] In some non-limiting embodiments or aspects, the at least one processor can be further programmed and / or configured to compare a value associated with a second key field of the settlement record to a value associated with a second key field of the one or more authorization records. The second key field of the settlement record can correspond to the second key field of the one or more authorization records. Determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining, based on comparing the value associated with the second key field of the settlement record to the value associated with the second key field of the one or more authorization records, that the settlement record corresponds to the authorization record among the one or more authorization records. The first key field can be associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and the second key field can be associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0021] In some non-limiting embodiments or aspects, determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record. The at least one processor can be further programmed and / or configured to determine, based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, that the settlement record partially matches the authorization record.

[0022] In some non-limiting embodiments or aspects, generating the updated settlement record can include providing the settlement record and the authorization record as input to a machine learning model and generating, based on providing the settlement record and the authorization record as the input to the machine learning model, a prediction associated with a confidence score that the settlement record matches the authorization record. Generating the updated settlement record can further include updating the settlement record based on the confidence score.

[0023] According to some non-limiting embodiments or aspects, a computer program product for determining non-indexed record correspondence is provided. The computer program product can include a non-transitory computer-readable medium storing program instructions configured to cause at least one processor to receive a clearing record comprising at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network. The program instructions can be configured to cause the at least one processor to compare a value associated with a first key field of the clearing record to a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records. The one or more authorization records can be associated with an authorization request for a payment transaction of the one or more payment transactions. The program instructions can be configured to cause the at least one processor to determine that the clearing record corresponds to an authorization record among the one or more authorization records based on comparing the value associated with the first key field of the clearing record to the value associated with the first key field of the one or more authorization records. The program instructions can be configured to cause the at least one processor to generate an updated clearing record based on determining that the clearing record corresponds to the authorization record. The program instructions can be configured to cause the at least one processor to transmit the updated clearing record.

[0024] In some non-limiting embodiments or aspects, receiving the clearing record associated with the one or more payment transactions can include receiving a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions. The program instructions can be further configured to cause the at least one processor to normalize one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with an issuer system. When normalizing the one or more clearing records of the clearing batch file, the at least one processor can convert one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0025] In some non-limiting embodiments or aspects, the program instructions can further cause the at least one processor to compare a value associated with a second key field of the settlement record to a value associated with a second key field of the one or more authorization records, the second key field of the settlement record corresponding to the second key field of the one or more authorization records. Determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining, based on comparing the value associated with the second key field of the settlement record to the value associated with the second key field of the one or more authorization records, that the settlement record corresponds to the authorization record among the one or more authorization records. The first key field can be associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and the second key field can be associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0026] In some non-limiting embodiments or aspects, determining that the settlement record corresponds to the authorization record among the one or more authorization records can include determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record. The program instructions can be further configured to cause the at least one processor to determine, based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, that the settlement record partially matches the authorization record.

[0027] In some non-limiting embodiments or aspects, generating the updated settlement record can include providing the settlement record and the authorization record as input to a machine learning model and generating, based on providing the settlement record and the authorization record as the input to the machine learning model, a prediction associated with a confidence score that the settlement record matches the authorization record. Generating the updated settlement record can further include updating the settlement record based on the confidence score.

[0028] Other non-limiting embodiments or aspects of the present disclosure will be set forth in the following numbered clauses:

[0029] Clause 1 : A computer-implemented method comprising: receiving, by at least one processor, a clearing record comprising at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network; comparing, by at least one processor, a value associated with a first key field of the clearing record and a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records, wherein the one or more authorization records are associated with an authorization request for a payment transaction of the one or more payment transactions; determining, by at least one processor, that the clearing record corresponds to an authorization record among the one or more authorization records based on comparing the value associated with the first key field of the clearing record and the value associated with the first key field of the one or more authorization records; generating, by at least one processor, an updated clearing record based on determining that the clearing record corresponds to the authorization record; and transmitting, by at least one processor, the updated clearing record.

[0030] Clause 2: The computer-implemented method of clause 1, wherein receiving the clearing record associated with the one or more payment transactions comprises receiving, by at least one processor, a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions, the computer-implemented method further comprising normalizing, by at least one processor, one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with an issuer system, wherein, when normalizing the one or more clearing records of the clearing batch file, the at least one processor converts one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0031] Clause 3: The computer-implemented method of clause 1 or 2, further comprising: comparing, by the at least one processor, a value associated with a second key field of the settlement record to a value associated with a second key field of the one or more authorization records, the second key field of the settlement record corresponding to the second key field of the one or more authorization records, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining, by the at least one processor, that the settlement record corresponds to the authorization record among the one or more authorization records based on comparing the value associated with the second key field of the settlement record to the value associated with the second key field of the one or more authorization records; wherein the first key field is associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and wherein the second key field is associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0032] Clause 4: The computer-implemented method of any of clauses 1 to 3, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining, by the at least one processor, that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record; and determining, by the at least one processor, that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, the computer-implemented method further comprising: determining, by the at least one processor, that the settlement record partially matches the authorization record based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record.

[0033] Clause 5: The computer-implemented method of any one of clauses 1-4, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining, by the at least one processor, that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record; and determining, by the at least one processor, that the value associated with the second key field of the settlement record matches the value associated with the second key field of the authorization record, the computer-implemented method further comprising: determining, by the at least one processor, that the settlement record matches the authorization record based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record matches the value associated with the second key field of the authorization record.

[0034] Clause 6: The computer-implemented method of any one of clauses 1-5, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining, by the at least one processor, that the value associated with the first key field of the settlement record does not match the value associated with the first key field of the authorization record; and determining, by the at least one processor, that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, the computer-implemented method further comprising: determining, by the at least one processor, that the settlement record does not match the authorization record based on determining that the value associated with the first key field of the settlement record does not match the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record.

[0035] Clause 7: The computer-implemented method of any one of clauses 1-6, wherein generating the updated settlement record comprises: providing, by the at least one processor, the settlement record and the authorization record as input to a machine learning model; generating, by the at least one processor, a prediction associated with a confidence score that the settlement record matches the authorization record based on providing the settlement record and the authorization record as the input to the machine learning model; and updating, by the at least one processor, the settlement record based on the confidence score.

[0036] Clause 8: The computer-implemented method of any one of clauses 1-7, wherein updating the clearing record based on the confidence score comprises at least one of: appending, by the at least one processor, the confidence score to the clearing record; appending, by the at least one processor, an initial transaction amount of the authorization record to the clearing record; and appending, by the at least one processor, a transaction identifier of the authorization record to the clearing record.

[0037] Clause 9: The computer-implemented method of any one of clauses 1-8, further comprising generating, by the at least one processor, an updated clearing batch file based on the clearing batch file and the updated clearing record; wherein transmitting the updated clearing record comprises transmitting, by the at least one processor, the updated clearing batch file to an issuer system.

[0038] Clause 10: The computer-implemented method of any one of clauses 1-9, wherein generating the updated clearing record based on determining that the clearing record corresponds to the authorization record comprises: providing, by the at least one processor, the clearing record and the one or more authorization records to a machine learning model; generating, by the at least one processor, a prediction associated with a merchant transaction pattern and a confidence score based on providing the clearing record and the one or more authorization records to the machine learning model; and updating, by the at least one processor, the clearing record based on the merchant transaction pattern and the confidence score.

[0039] Clause 11: A system comprising a server, the server comprising at least one processor programmed and / or configured to: receive a clearing record comprising at least one key field, the clearing record associated with one or more payment transactions completed in a payment transaction processing network; compare a value associated with a first key field of the clearing record to a value associated with a first key field of one or more authorization records, the one or more authorization records associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records, wherein the one or more authorization records are associated with an authorization request for a payment transaction of the one or more payment transactions; determine, based on comparing the value associated with the first key field of the clearing record to the value associated with the first key field of the one or more authorization records, that the clearing record corresponds to an authorization record among the one or more authorization records; generate, based on determining that the clearing record corresponds to the authorization record, an updated clearing record; and transmit the updated clearing record.

[0040] Clause 12: The system of clause 11, wherein receiving the clearing record associated with the one or more payment transactions comprises receiving a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions, the at least one processor being further programmed and / or configured to: normalize one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with the issuer system, wherein, when normalizing the one or more clearing records of the clearing batch file, the at least one processor converts one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0041] Clause 13: The system of clause 11 or 12, wherein the at least one processor is further programmed and / or configured to: compare a value associated with a second key field of the clearing record to a value associated with a second key field of the one or more authorization records, the second key field of the clearing record corresponding to the second key field of the one or more authorization records, wherein determining that the clearing record corresponds to the authorization record among the one or more authorization records comprises determining that the clearing record corresponds to the authorization record among the one or more authorization records based on comparing the value associated with the second key field of the clearing record to the value associated with the second key field of the one or more authorization records; wherein the first key field is associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and wherein the second key field is associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0042] Clause 14: The system of any of clauses 11 to 13, wherein determining that the clearing record corresponds to the authorization record among the one or more authorization records comprises determining that the value associated with the first key field of the clearing record matches the value associated with the first key field of the authorization record and determining that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record, the at least one processor being further programmed and / or configured to: determine that the clearing record partially matches the authorization record based on determining that the value associated with the first key field of the clearing record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record.

[0043] Clause 15: The system of any one of clauses 11-14, wherein generating the updated clearing record comprises: providing the clearing record and the authorization record as input to a machine learning model; generating, based on providing the clearing record and the authorization record as the input to the machine learning model, a prediction associated with a confidence score that the clearing record matches the authorization record; and updating the clearing record based on the confidence score.

[0044] Clause 16: A computer program product comprising a non-transitory computer- readable medium storing program instructions configured to cause at least one processor to: receive a clearing record comprising at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network; compare a value associated with a first key field of the clearing record to a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more payment transactions authorized in the payment transaction processing network, the first key field of the clearing record corresponding to the first key field of the one or more authorization records, wherein the one or more authorization records are associated with an authorization request for a payment transaction of the one or more payment transactions; determine, based on comparing the value associated with the first key field of the clearing record to the value associated with the first key field of the one or more authorization records, that the clearing record corresponds to an authorization record among the one or more authorization records; generate, based on determining that the clearing record corresponds to the authorization record, an updated clearing record; and transmit the updated clearing record.

[0045] Clause 17: The computer program product of clause 16, wherein receiving the clearing record associated with the one or more payment transactions comprises: receiving a clearing batch file comprising a plurality of clearing records of a plurality of payment transactions, the program instructions further configured to cause the at least one processor to: normalize one or more clearing records of the plurality of clearing records of the clearing batch file based on a clearing record template associated with an issuer system, wherein, when normalizing the one or more clearing records of the clearing batch file, the at least one processor converts one or more values associated with one or more key fields of the one or more clearing records to one or more updated values.

[0046] Clause 18: The computer program product of clause 16 or 17, wherein the program instructions are further configured to cause the at least one processor to: compare a value associated with a second key field of the settlement record to a value associated with a second key field of the one or more authorization records, the second key field of the settlement record corresponding to the second key field of the one or more authorization records, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining, based on comparing the value associated with the second key field of the settlement record to the value associated with the second key field of the one or more authorization records, that the settlement record corresponds to the authorization record among the one or more authorization records; wherein the first key field is associated with at least one of a transaction identifier, a transaction amount, and a payment account type, and wherein the second key field is associated with another of the at least one of the transaction identifier, the transaction amount, and the payment account type.

[0047] Clause 19: The computer program product of any one of clauses 16 to 18, wherein determining that the settlement record corresponds to the authorization record among the one or more authorization records comprises: determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record; and determining that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, the program instructions further configured to cause the at least one processor to: determine, based on determining that the value associated with the first key field of the settlement record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the settlement record does not match the value associated with the second key field of the authorization record, that the settlement record partially matches the authorization record.

[0048] Clause 20: The computer program product of any one of clauses 16 to 19, wherein generating the updated settlement record comprises: providing the settlement record and the authorization record as input to a machine learning model; generating, based on providing the settlement record and the authorization record as the input to the machine learning model, a prediction associated with a confidence score that the settlement record matches the authorization record; and updating the settlement record based on the confidence score.

[0049] These and other features and characteristics of the present disclosure, as well as the methods of operation and functions of the related elements of structures and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following description and appended claims with reference to the accompanying drawings, all of which form a part of this specification, wherein like reference numerals designate similar, but not necessarily identical components. It is to be expressly understood, however, that the drawings are for purposes of illustration only and are not intended as a definition of the limits of the disclosure. As used in the specification and in the claims, the singular form of "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. BRIEF DESCRIPTION OF DRAWINGS

[0050] Additional advantages and details of the present disclosure will become more fully apparent from the following description, taken in conjunction with the accompanying drawings, wherein:

[0051] Figure 1 is a diagram of a non-limiting embodiment or aspect of an example environment for determining non-indexed record correspondence;

[0052] Figure 2 is a diagram of a non-limiting embodiment or aspect of one or more apparatuses and / or components of one or more systems of Figure 1

[0053] Figure 3 is a flow diagram of a non-limiting embodiment or aspect of a process for determining non-indexed record correspondence;

[0054] Figure 4 is an operational diagram of a non-limiting embodiment or aspect of a process for determining non-indexed record correspondence;

[0055] Figure 5 is an operational diagram of a non-limiting embodiment or aspect of a first process used in a process for determining non-indexed record correspondence; and

[0056] Figure 6 is an operational diagram of a non-limiting embodiment or aspect of a second process used in a process for determining non-indexed record correspondence. DETAILED DESCRIPTION

[0057] ​For purposes of description herein, the terms "end," "upper," "lower," "right," "left," "vertical," "horizontal," "top," "bottom," "lateral," "longitudinal," and derivatives thereof shall relate to the disclosure as oriented in the drawings. However, it is to be understood that the disclosure can assume various alternative orientations and step sequences, except where expressly specified to the contrary. It is also to be understood that the specific devices and processes illustrated in the attached drawings, and described in the following specification, are simply exemplary embodiments or aspects of the disclosure. Hence, specific dimensions and other physical characteristics related to the embodiments or aspects disclosed herein are not to be considered as limiting, unless otherwise indicated.

[0058] No aspect, component, element, structure, act, step, function, instruction, etc. used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the article "a" is intended to include one or more items, and can be used interchangeably with "one or more" and "at least one." Furthermore, as used herein, the term "set" is intended to include one or more items (e.g., related items, unrelated items, a combination of related and unrelated items, etc.), and can be used interchangeably with "one or more" or "at least one." Where only one item is intended, the term "one" or similar language is used. Also, as used herein, the term "has," and its derivatives, is intended to include "consists of," "consisting of," "consisting essentially of," and / or the like. Also, as used herein, the phrase "based on" is intended to mean "based, at least in part, on" unless explicitly stated otherwise.

[0059] As used herein, the terms "communication" and "communicate" can refer to the reception, receipt, transmission, transfer, provision, and / or the like of information (e.g., data, signals, messages, instructions, commands, and / or the like). For one unit (e.g., device, system, component of a device or system, combination thereof, and / or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and / or transmit information to the other unit. This can refer to a direct or indirect connection that is wired and / or wireless in nature. Additionally, two units can be in communication with each other even though the information transmitted can be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit can be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit can be in communication with a second unit if at least one intermediary unit (e.g., a third unit positioned between the first and second units) processes information received from the first unit and transmits process information to the second unit. In some non-limiting embodiments or aspects, a message can refer to a network packet (e.g., data packet, and / or the like) that includes data.

[0060] As used herein, the term “issuer,” “issuer institution,” “issuer bank,” or “payment device issuer” can refer to one or more entities that provide accounts to individuals (e.g., users, customers, etc.) for conducting payment transactions, such as credit card payment transactions and / or debit card payment transactions. For example, an issuer institution can provide a customer with an account identifier, such as a primary account number (PAN), that uniquely identifies one or more accounts associated with the customer. In some non-limiting embodiments or aspects, an issuer can be associated with a bank identification number (BIN) that uniquely identifies the issuer institution. As used herein, an “issuer system” can refer to one or more computer systems operated by or on behalf of an issuer, such as a server executing one or more software applications. For example, an issuer system can include one or more authorization servers for authorizing transactions.

[0061] As used herein, the term “account identifier” can include one or more types of identifiers associated with an account (e.g., a PAN associated with an account, a card number associated with an account, a payment card number associated with an account, a token associated with an account, etc.). In some non-limiting embodiments or aspects, an issuer can provide a user with an account identifier (e.g., a PAN, a token, etc.) that uniquely identifies one or more accounts associated with the user. An account identifier can be embodied on a payment device (e.g., a physical instrument for conducting payment transactions, such as a payment card, a credit card, a debit card, a gift card, etc.) and / or can be electronic information communicated to a user that the user can use for electronic payment transactions. In some non-limiting embodiments or aspects, an account identifier can be an original account identifier, where the original account identifier is provided to a user when an account associated with the account identifier is created. In some non-limiting embodiments or aspects, an account identifier can be a supplemental account identifier, which can include an account identifier that is provided to a user after an original account identifier is provided to the user. For example, a supplemental account identifier can be provided to a user if the original account identifier is forgotten, stolen, etc. In some non-limiting embodiments or aspects, an account identifier can be directly or indirectly associated with an issuer institution, such that the account identifier can be a token that maps to a PAN or other type of account identifier. An account identifier can be any combination of alphanumeric, character, and / or symbol, etc.

[0062] As used herein, the term“token” can refer to an account identifier that is used as a substitute for or in place of another account identifier (e.g., a PAN). A token can be associated with a PAN or another original account identifier in one or more data structures (e.g., one or more databases, etc.) such that the token can be used to conduct payment transactions without the need to directly use the original account identifier. In some non-limiting embodiments or aspects, a PAN or other original account identifier can be associated with multiple tokens for different individuals or purposes. In some non-limiting embodiments or aspects, a token can be associated with a PAN or other account identifier in one or more data structures such that the token can be used to conduct transactions without the need to directly use the PAN or other account identifier. In some examples, a PAN or other account identifier can be associated with multiple tokens for different uses or purposes.

[0063] As used herein, the term“merchant” can refer to one or more entities (e.g., an operator of a retail business) that provide goods and / or services and / or access to goods and / or services to users (e.g., customers, patrons, etc.) based on transactions, such as payment transactions. As used herein, a“merchant system” can refer to one or more computer systems operated by or on behalf of a merchant, such as a server executing one or more software applications. As used herein, the term“product” can refer to one or more goods and / or services provided by a merchant.

[0064] As used herein, a“point-of-sale (POS) device” can refer to one or more devices that can be used by a merchant to conduct transactions (e.g., payment transactions) and / or process transactions. For example, a POS device can include one or more client devices. Additionally or alternatively, a POS device can include a peripheral device, a card reader, a scanning device (e.g., a code scanner), a communication receiver, a near-field communication (NFC) receiver, a radio-frequency identification (RFID) receiver, and / or other contactless transceiver or receiver, a contact-based receiver, a payment terminal, etc.

[0065] As used herein, the term“point-of-sale (POS) system” can refer to one or more client devices and / or peripheral devices used by a merchant to conduct transactions. For example, a POS system can include one or more POS devices, and / or other similar devices that can be used to conduct payment transactions. In some non-limiting embodiments or aspects, a POS system (e.g., a merchant POS system) can include one or more server computers programmed or configured to process online payment transactions through a web page, a mobile application, etc.

[0066] As used herein, the term “transaction service provider” can refer to an entity that receives transaction authorization requests from merchants or other entities and, in some cases, provides payment guarantees through agreements between the transaction service provider and issuer institutions. For example, a transaction service provider can include a payment network, such as American or any other entity that processes transactions. As used herein, the term “transaction processing system” can refer to one or more computer systems operated by or on behalf of a transaction service provider, such as a transaction processing system executing one or more software applications. A transaction processing system can include one or more processors and, in some non-limiting embodiments or aspects, can be operated by or on behalf of a transaction service provider.

[0067] As used herein, the term “acquirer” can refer to an entity that is licensed by and approved by a transaction service provider to initiate transactions (e.g., payment transactions) involving payment devices associated with the transaction service provider. As used herein, the term “acquirer system” can also refer to one or more computer systems, computer devices, or the like operated by or on behalf of an acquirer. Transactions that an acquirer can initiate can include payment transactions (e.g., purchases, original credit transactions (OCTs), account funding transactions (AFTs), and the like). In some non-limiting embodiments or aspects, an acquirer can be authorized by a transaction service provider to contract with merchants or service providers to initiate transactions involving payment devices associated with the transaction service provider. An acquirer can contract with a payment servicer to enable the payment servicer to offer sponsorship to merchants. An acquirer can monitor the compliance of a payment servicer according to transaction service provider regulations. An acquirer can conduct due diligence on a payment servicer and ensure that proper due diligence occurs prior to contracting with a sponsored merchant. An acquirer can be liable for all transaction service provider programs operated or sponsored by the acquirer. An acquirer can be responsible for the actions of acquirer payment servicers, merchants sponsored by acquirer payment servicers, and the like. In some non-limiting embodiments or aspects, an acquirer can be a financial institution, such as a bank.

[0068] As used herein, the term “payment gateway” can refer to an entity and / or a payment processing system operated by or on behalf of such an entity (e.g., a merchant service provider, a payment service provider, a payment facilitator, a payment facilitator under contract with an acquirer, a payment aggregator, etc.) that provides payment services (e.g., transaction service provider payment services, payment processing services, etc.) to one or more merchants. The payment services can be associated with the use of portable financial devices managed by a transaction service provider. As used herein, the term “payment gateway system” can refer to one or more computer systems, computer devices, servers, groups of servers, etc. operated by or on behalf of a payment gateway.

[0069] As used herein, the terms “electronic wallet,” “electronic wallet mobile application,” and “digital wallet” can refer to one or more electronic devices, including one or more software applications, configured to initiate and / or conduct a transaction (e.g., a payment transaction, an electronic payment transaction, etc.). For example, an electronic wallet can include a user device (e.g., a mobile device) executing an application, as well as server-side software and / or databases for maintaining and providing data to the user device to be used during a payment transaction. As used herein, the term “electronic wallet provider” can include an entity that provides and / or maintains an electronic wallet and / or an electronic wallet mobile application for users (e.g., customers). Examples of electronic wallet providers include, but are not limited to, Google Android Apple and Samsung In some non-limiting examples, a financial institution (e.g., an issuer institution) can be an electronic wallet provider. As used herein, the term “electronic wallet provider system” can refer to one or more computer systems, computer devices, servers, groups of servers, etc. operated by or on behalf of an electronic wallet provider.

[0070] As used herein, the term “payment device” can refer to a payment card (e.g., a credit or debit card), a gift card, a smart card, a smart media, a payroll card, a healthcare card, a wristband, a machine-readable medium containing account information, a keychain device or fob, an RFID transponder, a retailer discount or membership card, etc. A payment device can include volatile or non-volatile memory to store information (e.g., an account identifier, an account holder’s name, etc.).

[0071] As used herein, the terms "client" and "client device" can refer to one or more computing devices, such as processors, storage devices, and / or similar computer components that access services provided by a server. In some non-limiting embodiments or aspects, a "client device" can refer to one or more devices that facilitate a payment transaction, such as a POS device and / or POS system used by a merchant. In some non-limiting embodiments or aspects, a client device can include an electronic device configured to communicate with one or more networks and / or facilitate a payment transaction, such as, but not limited to, one or more desktop computers, one or more portable computers (e.g., tablet computers), one or more mobile devices (e.g., cellular phones, smartphones, personal digital assistants (PDAs), wearable devices such as watches, glasses, lenses, and / or clothing, etc.), and / or other similar devices. Further, a "client" can also refer to an entity that owns, utilizes, and / or operates a client device to facilitate a payment transaction with a transaction service provider, such as a merchant.

[0072] As used herein, the term "server" can refer to one or more computing devices, such as processors, storage devices, and / or similar computer components, that communicate with client devices and / or other computing devices over a network, such as the Internet or a private network, and in some examples, facilitate communication between other servers and / or client devices.

[0073] As used herein, the term "system" can refer to one or more computing devices or combinations of computing devices, such as, but not limited to, processors, servers, client devices, software applications, and / or other similar components. Further, as used herein, a reference to a "server" or a "processor" can refer to a previously recited server and / or processor recited as performing a previous step or function, a different server and / or processor, and / or a combination of servers and / or processors. For example, as used in the specification and claims, a first server and / or a first processor recited as performing a first step or function can refer to the same or a different server and / or processor recited as performing a second step or function.

[0074] As used herein, "clearing record" can refer to a transmitted data object sent from an acquirer system to a transaction processing system that can be transmitted to an issuer system, modified or unmodified, and can be associated with a settlement transaction, dispute, dispute response, acquirer initiated pre-arbitration, chargeback, adjustment, etc. in a format necessary for the settlement exchange to present. "Clearing" can refer to the process of a transaction processing system receiving a clearing record from an acquirer system and transmitting the clearing record to an issuer system to complete a transaction (e.g., a credit card transaction), chargeback a transaction, or process a fee collection transaction. "Settlement" can refer to the reporting and transfer of an amount owed by one entity account to another entity account or transaction processing system as a result of clearing. As used herein, "authorization record" can refer to a transmitted data object sent from an acquirer system to an issuer system, directly or indirectly (e.g., via a transaction processing system), that can be associated with an authorized payment amount from one entity account to another. Received clearing records can be matched with authorization records for settlement of transactions.

[0075] By implementing the systems, methods, and computer program products described herein, systems can be implemented that enable issuer institutions to more quickly and accurately determine whether an authorization record corresponds to a clearing record. For example, systems can be implemented as described herein to determine whether a clearing record corresponds to an authorization record where an approved transaction amount specified in the authorization record differs from an approved transaction amount specified in the clearing record (e.g., where a tip greater than an amount permitted by the issuer institution was added to the approved transaction amount). Accordingly, these systems can more accurately determine that an authorization record corresponds to a clearing record. This, in turn, can reduce the time such systems can need to process a payment transaction. Additionally or alternatively, an issuer institution involved in a payment transaction can forego processing the payment transaction as a forced post payment transaction based on determining that a clearing record corresponds to an authorization record, which can subsequently avoid issuing a chargeback, thereby reducing consumption of network resources (e.g., computer processing capacity, time, bandwidth, etc.).

[0076] Referring now to Figure 1 , a diagram of an example environment 100 in which devices, systems, methods, and / or products described herein can be implemented is provided. As shown in Figure 1 , environment 100 includes a transaction processing network 101, a user device 102, a merchant system 104, a payment gateway system 106, an acquirer system 108, a transaction processing system 110, an issuer system 112, and / or a communication network 114. Transaction processing network 101, user device 102, merchant system 104, payment gateway system 106, acquirer system 108, transaction processing system 110, and / or issuer system 112 can be interconnected (e.g., establish connections to communicate, etc.) by a wired connection, a wireless connection, or a combination of wired and wireless connections.

[0077] The user device 102 can include one or more devices configured to communicate with the merchant system 104, the payment gateway system 106, the acquirer system 108, the transaction processing system 110, and / or the issuer system 112 via the communication network 114. For example, the user device 102 can include a payment device, a smartphone, a tablet, a laptop, a desktop computer, etc. The user device 102 can be configured to transmit data to and / or receive data from the merchant system 104 via an imaging system and / or a short-range wireless communication connection (e.g., a near-field communication (NFC) connection, a radio-frequency identification (RFID) communication connection, In some non-limiting embodiments or aspects, the user device 102 can be associated with a user (e.g., an individual operating the device).

[0078] The merchant system 104 can include one or more devices configured to communicate with the user device 102, the payment gateway system 106, the acquirer system 108, the transaction processing system 110, and / or the issuer system 112 via the communication network 114. For example, the merchant system 104 can include one or more servers, a group or groups of servers, one or more client devices, a group or groups of client devices, etc. In some non-limiting embodiments or aspects, the merchant system 104 can include a point-of-sale (POS) device. In some non-limiting embodiments or aspects, the merchant system 104 can be associated with a merchant as described herein.

[0079] The payment gateway system 106 can include one or more devices configured to communicate with the user device 102, the merchant system 104, the acquirer system 108, the transaction processing system 110, and / or the issuer system 112 via the communication network 114. For example, the payment gateway system 106 can include one or more servers, a group or groups of servers, etc. In some non-limiting embodiments or aspects, the payment gateway system 106 can be associated with a payment gateway as described herein.

[0080] The acquirer system 108 can include one or more devices configured to communicate with the user device 102, the merchant system 104, the payment gateway system 106, the transaction processing system 110, and / or the issuer system 112 via the communication network 114. For example, the acquirer system 108 can include one or more servers, a group or groups of servers, etc. In some non-limiting embodiments or aspects, the acquirer system 108 can be associated with an acquirer as described herein.

[0081] The transaction processing system 110 can include one or more devices configured to communicate with the user device 102, the merchant system 104, the payment gateway system 106, the acquirer system 108, and / or the issuer system 112 via the communication network 114. For example, the transaction processing system 110 can include one or more servers (e.g., transaction processing servers), one or more groups of servers, and / or the like. In some non-limiting embodiments or aspects, the transaction processing system 110 can be associated with a transaction service provider described herein.

[0082] The issuer system 112 can include one or more devices configured to communicate with the user device 102, the merchant system 104, the payment gateway system 106, the acquirer system 108, and / or the transaction processing system 110 via the communication network 114. For example, the issuer system 112 can include one or more servers, one or more groups of servers, and / or the like. In some non-limiting embodiments or aspects, the issuer system 112 can be associated with an issuer institution that issues payment accounts and / or instruments (e.g., credit accounts, debit accounts, credit cards, debit cards, and / or the like) to users (e.g., users associated with the user device 102, and / or the like).

[0083] In some non-limiting embodiments or aspects, the transaction processing network 101 can include one or more systems in a communication path for processing transactions. For example, the transaction processing network 101 can include the merchant system 104, the payment gateway system 106, the acquirer system 108, the transaction processing system 110, and / or the issuer system 112 in a communication path (e.g., a communication path, a communication channel, a communication network, and / or the like). For example, the transaction processing network 101 can process (e.g., initiate, conduct, authorize, and / or the like) an electronic payment transaction via a communication path between the merchant system 104, the payment gateway system 106, the acquirer system 108, the transaction processing system 110, and / or the issuer system 112.

[0084] The communication network 114 can include one or more wired and / or wireless networks. For example, the communication network 114 can include a cellular network (e.g., a long-term evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a code division multiple access (CDMA) network, and / or the like), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., a

[0085] The number and arrangement of systems and / or devices shown in FIG. 1 are provided as an example. There can be additional systems and / or devices, fewer systems and / or devices, different systems and / or devices, or differently arranged systems and / or devices than those shown in FIG. 1. For example, a system and / or device can be located on a different network than those shown in FIG. 1. Figure 1 The number and arrangement of systems and / or devices shown in FIG. 1 are provided as an example. There can be additional systems and / or devices, fewer systems and / or devices, different systems and / or devices, or differently arranged systems and / or devices than those shown in FIG. 1. For example, a system and / or device can be located on a different network than those shown in FIG. 1.Figure 1 The systems and / or devices shown arranged in different manners than those shown. Moreover, one or more functions described as being performed by a system and / or a device can be implemented within a single system and / or a single device, or Figure 1 two or more systems and / or devices shown, or Figure 1 a single system or a single device shown can be implemented as multiple distributed systems or devices. Additionally or alternatively, a set of systems or a set of devices of the environment 100 (e.g., one or more systems, one or more devices) can perform one or more functions described as being performed by another set of systems or another set of devices of the environment 100.

[0086] Reference is now made to Figure 2 FIG. 1 shows a diagram of example components of a device 200. The device 200 can correspond to one or more devices of the transaction processing network 101, one or more devices of the user devices 102 (e.g., one or more devices of a system of the user devices 102), one or more devices of the merchant systems 104, one or more devices of the payment gateway system 106, one or more devices of the acquirer system 108, one or more devices of the transaction processing system 110, one or more devices of the issuer system 112, and / or one or more devices of the communication network 114. In some non-limiting embodiments or aspects, one or more devices of the user devices 102, one or more devices of the merchant systems 104, one or more devices of the payment gateway system 106, one or more devices of the acquirer system 108, one or more devices of the transaction processing system 110, one or more devices of the issuer system 112, and / or one or more devices of the communication network 114 can include at least one device 200 and / or at least one component of the device 200. As Figure 2 shown, the device 200 can include a bus 202, a processor 204, a memory 206, a storage component 208, an input component 210, an output component 212, and a communication interface 214.

[0087] The bus 202 can include a component that permits communication among the components of the device 200. In some non-limiting embodiments or aspects, the processor 204 can be implemented in hardware, software, or a combination of hardware and software. For example, the processor 204 can include a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), etc.), a microprocessor, a digital signal processor (DSP), and / or any processing component that can be programmed to perform a function (e.g., a field programmable gate array (FPGA), an application- specific integrated circuit (ASIC), etc.). The memory 206 can include a random access memory (RAM), a read only memory (ROM), and / or another type of dynamic or static storage (e.g., flash memory, magnetic storage, optical storage, etc.) that stores information and / or instructions for use by the processor 204.

[0088] Storage component 208 can store information and / or software related to the operation and use of device 200. For example, storage component 208 can include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, a solid state disk, etc.), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of computer- readable medium, along with a corresponding drive.

[0089] Input component 210 can include a component that permits device 200 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, a camera, etc.). Additionally, or alternatively, input component 210 can include a sensor (e.g., a global positioning system (GPS) component, an accelerometer, a gyroscope, an actuator, etc.) for sensing information. Output component 212 can include a component that provides output information from device 200 (e.g., a display, a speaker, one or more light-emitting diodes (LEDs), etc.).

[0090] Communication interface 214 can include a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, etc.) that enables device 200 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 214 can permit device 200 to receive information from another device and / or provide information to another device. For example, communication interface 214 can include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a Bluetooth® interface, or the like.

[0091] Device 200 can perform one or more processes described herein. Device 200 can perform these processes based on processor 204 executing software instructions stored by a computer-readable medium, such as memory 206 and / or storage component 208. A computer-readable medium (e.g., a non-transitory computer-readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes a memory space located inside of a single physical storage device or spread across multiple physical storage devices.

[0092] The software instructions can be read into memory 206 and / or storage component 208 from another computer-readable medium or from another device via communication interface 214. When executed, the software instructions stored in memory 206 and / or storage component 208 can cause processor 204 to perform one or more processes described herein. Additionally, or alternatively, hardwired circuitry can be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments or aspects described herein are not limited to any specific combination of hardware circuitry and software. ​

[0093] Memory 206 and / or storage component 208 can include a data store or one or more data structures (e.g., a database, etc.). Device 200 can receive information from, store information in, communicate information to, or retrieve information from the data store or one or more data structures in memory 206 and / or storage component 208. For example, the information can include clearing record data, input data, output data, transaction data, account data, or any combination thereof.

[0094] The number and arrangement of components shown in FIG. 6 are provided as an example. In some non-limiting embodiments or aspects, device 200 can include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 6. Additionally or alternatively, a set of components (e.g., one or more components) of device 200 can perform one or more functions described as being performed by another set of components of device 200. Figure 2 The number and arrangement of components shown in FIG. 6 are provided as an example. In some non-limiting embodiments or aspects, device 200 can include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 6. Additionally or alternatively, a set of components (e.g., one or more components) of device 200 can perform one or more functions described as being performed by another set of components of device 200. Figure 2 The number and arrangement of components shown in FIG. 6 are provided as an example. In some non-limiting embodiments or aspects, device 200 can include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 6. Additionally or alternatively, a set of components (e.g., one or more components) of device 200 can perform one or more functions described as being performed by another set of components of device 200.

[0095] Referring now to FIG. 3, a flow diagram of non-limiting aspects or embodiments of a process 300 for determining non-indexed record correspondence is shown. In some non-limiting embodiments or aspects, one or more functions described with respect to process 300 can be performed by transaction processing system 110 (e.g., entirely, partially, etc.). In some non-limiting embodiments or aspects, one or more steps of process 300 can be performed by another device or set of devices separate from and / or including transaction processing system 110 (e.g., user device 102, merchant system 104, payment gateway system 106, acquirer system 108, and / or issuer system 112) (e.g., entirely, partially, etc.). Figure 3 As

[0096] Figure 3 ​As shown, in step 302, process 300 may include receiving a clearing record. For example, transaction processing system 110 may receive a clearing record. In such an example, transaction processing system 110 may receive a clearing record from acquiring system 108. In some non-limiting embodiments or aspects, the clearing record may be associated with a payment transaction. In some non-limiting embodiments or aspects, the clearing record may be associated with a payment transaction involving a user associated with user device 102 and a merchant associated with merchant system 104 and / or initiated by them. In some non-limiting embodiments or aspects, the clearing record may include one or more key fields (e.g., transaction data fields). Transaction records (e.g., clearing records, authorization records) may include multiple data fields, such as transaction data fields. Transaction data fields may include data fields specifying transaction record parameters. Examples of transaction data fields may include, but are not limited to, payment device identifier, transaction type (e.g., credit, debit, etc.), payment account type (e.g., debit account, credit account, etc.), payment device input type (e.g., refresh, keyboard, etc.), payment device expiration date, transaction amount, transaction identifier, etc. In some non-limiting embodiments or aspects, clearing records may be associated with one or more payment transactions completed in a payment processing network.

[0097] In some non-limiting embodiments or aspects, transaction processing system 110 may receive clearing batch files. For example, transaction processing system 110 may receive clearing batch files from acquiring system 108. In some non-limiting embodiments or aspects, clearing batch files may be electronic files comprising multiple clearing records, wherein each clearing record in the clearing batch file is associated with a payment transaction. For example, a clearing batch file may include multiple clearing records, wherein each clearing record in the clearing batch file is associated with a payment transaction in one or more payment transactions aggregated by acquiring system 108. In such examples, acquiring system 108 may aggregate multiple clearing records over a period of time (e.g., one day, one week, etc.). In some non-limiting embodiments or aspects, transaction processing system 110 may generate and transmit clearing batch files. For example, based on receiving multiple clearing records, transaction processing system 110 may generate and transmit clearing batch files. In such examples, multiple clearing records may be associated with payment transactions involving one or more merchant systems 104 and one or more user devices 102.

[0098] In some non-limiting embodiments or aspects, a payment transaction may be associated with an authorization record. For example, a payment transaction may be associated with an authorization record generated by the transaction processing system 110. In such examples, the transaction processing system 110 may generate an authorization record based on transaction data associated with the payment transaction received by the transaction processing system 110. In some non-limiting embodiments or aspects, the transaction processing system 110 may receive transaction data associated with the payment transaction from the merchant system 104. For example, the transaction processing system 110 may receive transaction data associated with the payment transaction from the merchant system 104 based on the user device 102 initiating the payment transaction at the merchant system 104.

[0099] In some non-limiting embodiments or aspects, transaction processing system 110 may receive an authorization record. For example, transaction processing system 110 may receive an authorization record from issuing system 112. In some non-limiting embodiments or aspects, transaction processing system 110 may receive an authorization record from issuing system 112 based on the initiation of a payment transaction associated with the authorization record. For example, transaction processing system 110 may receive an authorization record from issuing system 112 based on a payment transaction associated with the authorization record initiated by user device 102 at merchant system 104. In such examples, issuing system 112 may participate in the payment transaction. In some non-limiting embodiments or aspects, the authorization record may include one or more key fields associated with a value. For example, the authorization record may include one or more key fields associated with (e.g., may partially and / or fully correspond to) one or more key fields of a clearing record, as described herein.

[0100] In some non-limiting embodiments or aspects, transaction processing system 110 may normalize one or more clearing records. For example, transaction processing system 110 may normalize one or more clearing records from a plurality of clearing records in a clearing batch file. In some non-limiting embodiments or aspects, transaction processing system 110 may normalize one or more clearing records based on a clearing record template, which may be an electronic file defining a predetermined data field format including key fields of clearing records. For example, transaction processing system 110 may normalize one or more clearing records based on a clearing record template associated with issuer system 112. In some non-limiting embodiments or aspects, transaction processing system 110 may normalize one or more clearing records based on converting values ​​associated with one or more key values ​​of one or more clearing records to updated values. For example, transaction processing system 110 may normalize one or more clearing records based on a clearing record template based on converting values ​​associated with one or more key values ​​of one or more clearing records to updated values. In such an example, transaction processing system 110 can convert the transaction amount associated with the key value of the clearing record from "$10.45" to "1045".

[0101] like Figure 3 As shown, in step 304, process 300 may include comparing a value associated with a first key field of a clearing record with a value associated with a first key field of one or more authorization records. For example, transaction processing system 110 may compare a value associated with a first key field of a clearing record with a value associated with a first key field of one or more authorization records. In some non-limiting embodiments or aspects, the first key field of a clearing record may correspond to a first key field of one or more authorization records. For example, based on the fact that both the first key field of the clearing record and the first key fields of one or more authorization records specify a key field in one or more key fields (e.g., a transaction identifier for at least one payment transaction, the transaction amount for the payment transaction, the payment account type for the payment transaction, etc.), the first key field of the clearing record may correspond to a first key field of one or more authorization records, as described herein.

[0102] In some non-limiting embodiments or aspects, based on the transaction processing system 110 receiving clearing records, the transaction processing system 110 can compare the value associated with a first key field of the clearing record with a value associated with a first key field of one or more authorized records. For example, based on the transaction processing system 110 receiving clearing records from the acquiring system 108, the transaction processing system 110 can compare the value associated with a first key field of the clearing record with a value associated with a first key field of one or more authorized records. In another example, based on the transaction processing system 110 receiving clearing records in the form of clearing batch files, the transaction processing system 110 can compare the value associated with a first key field of the clearing record with a value associated with a first key field of one or more authorized records. In such examples, the transaction processing system 110 may receive clearing batch files from the acquiring system 108. In some non-limiting embodiments or aspects, based on the transaction processing system 110 determining that a first key field of the clearing record corresponds to a first key field of one or more authorized records, the transaction processing system 110 can compare the value associated with the first key field of the clearing record with a value associated with a first key field of one or more authorized records.

[0103] In some non-limiting embodiments or aspects, the transaction processing system 110 may compare multiple values ​​associated with multiple key fields of a clearing record and multiple values ​​associated with multiple key fields of one or more authorization records. For example, the transaction processing system 110 may compare multiple values ​​associated with multiple key fields of a clearing record included in a clearing batch file and multiple values ​​associated with multiple key fields of one or more authorization records. In some non-limiting embodiments or aspects, based on whether the transaction processing system 110 determines whether one or more values ​​associated with one or more key fields of a clearing record are associated with one or more values ​​associated with one or more key fields of one or more authorization records (e.g., matching, corresponding, etc.), the transaction processing system 110 may compare multiple values ​​associated with multiple key fields of a clearing record and multiple values ​​associated with multiple key fields of one or more authorization records. For example, the transaction processing system 110 may determine that a first value associated with a first key field of a clearing record is associated with a first value associated with a first key field of an authorization record. In such an example, transaction processing system 110 may compare one or more values ​​associated with one or more key fields of a clearing record (e.g., different key fields from a first key field) with one or more key fields of one or more authorization records (e.g., different key fields from a first key field). In such an example, based on transaction processing system 110 determining that a first value of the first key field of the clearing record is associated with a first value of the first key field of one or more authorization records, transaction processing system 110 may determine that the compared values ​​associated with the key fields of one or more authorization records and the values ​​associated with the key fields of the clearing record correspond to each other.

[0104] In some non-limiting embodiments or aspects, clearing records and / or one or more authorization records may be associated with one or more payment transactions authorized in the payment transaction processing network. For example, clearing records and / or one or more authorization records may be associated with one or more payment transactions processed by transaction processing system 110 in the payment transaction processing network. In some non-limiting embodiments or aspects, authorization records may be associated with and / or include transaction data associated with payment transactions involving user device 102 and merchant system 104.

[0105] like Figure 3As shown, in step 306, process 300 may include determining whether a clearing record corresponds to an authorized record among one or more authorized records. For example, transaction processing system 110 may determine whether a clearing record corresponds to an authorized record among one or more authorized records. In such an example, transaction processing system 110 may determine whether a clearing record corresponds to an authorized record among one or more authorized records by comparing one or more values ​​associated with one or more key fields of a clearing record with one or more values ​​associated with one or more key fields of one or more authorized records.

[0106] In one example, based on transaction processing system 110 determining that a value associated with a first key field of a clearing record matches a value associated with a first key field of an authorization record, transaction processing system 110 can determine whether a clearing record corresponds to an authorization record among one or more authorization records. In such an example, based on transaction processing system 110 determining that a value associated with a second key field of a clearing record does not match a value associated with a second key field of an authorization record, transaction processing system 110 can also determine that a clearing record corresponds to an authorization record. In some non-limiting embodiments or aspects, based on transaction processing system 110 determining that a value associated with a first key field of a clearing record matches a value associated with a first key field of an authorization record, and a value associated with a second key field of a clearing record does not match a value associated with a second key field of an authorization record, transaction processing system 110 can determine that a clearing record partially matches an authorization record.

[0107] In this example, based on the transaction processing system 110 determining that the value associated with a first key field of a clearing record matches the value associated with a first key field of an authorization record, the transaction processing system 110 can determine whether the clearing record corresponds to an authorization record among one or more authorization records. In such an example, the transaction processing system 110 can also determine that the value associated with a second key field of the clearing record matches the value associated with a second key field of the authorization record. In some non-limiting embodiments or aspects, based on the transaction processing system 110 determining that the value associated with a first key field of the clearing record matches the value associated with a first key field of the authorization record, and that the value associated with a second key field of the clearing record matches the value associated with a second key field of the authorization record, the transaction processing system 110 can determine that the clearing record matches an authorization record.

[0108] In this example, based on the transaction processing system 110 determining that the value associated with the first key field of the clearing record does not match the value associated with the first key field of the authorization record, the transaction processing system 110 can determine whether the clearing record corresponds to an authorization record among one or more authorization records. In such an example, the transaction processing system 110 can also determine that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record. In some non-limiting embodiments or aspects, based on the transaction processing system 110 determining that the value associated with the first key field of the clearing record does not match the value associated with the first key field of the authorization record, and that the value associated with the second key field of the clearing record does not match the value associated with the second key field of the authorization record, the transaction processing system 110 can determine that the clearing record does not match the authorization record.

[0109] like Figure 3 As shown, in step 308, process 300 may include generating an updated clearing record. For example, transaction processing system 110 may generate an updated clearing record, such as a clearing record with modified and / or additional data. In some non-limiting embodiments or aspects, transaction processing system 110 may generate an updated clearing record based on determining that the clearing record corresponds to one or more authorization records. For example, transaction processing system 110 may generate an updated clearing record based on determining that the clearing record does not match, partially matches, and / or matches one or more authorization records.

[0110] In some non-limiting embodiments or aspects, the transaction processing system 110 may provide clearing records and authorization records as input to a machine learning model. For example, based on the transaction processing system 110 determining that a clearing record corresponds to an authorization record, the transaction processing system 110 may provide the clearing record and authorization record as input to the machine learning model. In such examples, based on the transaction processing system 110 providing the clearing record and authorization record as input to the machine learning model, the transaction processing system 110 may generate a prediction (e.g., an output indicating the probability that the clearing record matches the authorization record). The prediction may be associated with a confidence score (e.g., a score indicating the probability that the clearing record matches and / or partially matches the authorization record). In some non-limiting embodiments or aspects, the transaction processing system 110 may generate updated clearing records based on the confidence score. In some non-limiting embodiments or aspects, based on the transaction processing system 110 attaching the confidence score to the clearing record, the transaction processing system 110 may generate updated clearing records. In some non-limiting embodiments or aspects, based on the initial transaction amount of the authorization record being appended to the clearing record by the transaction processing system 110, the transaction processing system 110 can generate an updated clearing record. For example, based on the transaction processing system 110 determining that the authorization record matches and / or partially matches the clearing record, the transaction processing system 110 can append the initial transaction amount of the authorization record to the clearing record. In some non-limiting embodiments or aspects, based on the transaction processing system 110 appending the transaction identifier of the authorization record to the clearing record, the transaction processing system 110 can generate an updated clearing record. For example, based on the transaction processing system 110 determining that the authorization record matches and / or partially matches the clearing record and appending the transaction identifier of the authorization record to the clearing record, the transaction processing system 110 can generate a clearing record.

[0111] In some non-limiting embodiments or aspects, the transaction processing system 110 may generate updated clearing batch files, such as clearing batch files that include one or more updated clearing records and / or one or more added or deleted clearing records. For example, based on the transaction processing system 110 determining that the clearing records included in the clearing batch file correspond to one or more authorized records, the transaction processing system 110 may generate updated clearing batch files. In some non-limiting embodiments or aspects, the transaction processing system 110 may generate updated clearing batch files based on clearing batch files received by the transaction processing system 110 and one or more updated clearing records generated by the transaction processing system 110.

[0112] In some non-limiting embodiments or aspects, based on the transaction processing system 110 including merchant transaction patterns and / or confidence scores with clearing records, the transaction processing system 110 can generate updated clearing records. Merchant transaction patterns may include one or more trends, arrangements, changes, skews, and / or ranges of values ​​in transaction data fields associated with the merchant, and can be derived by analyzing historical transactions associated with a given merchant. For example, the transaction processing system 110 may provide clearing records and one or more authorization records to a machine learning model. In some non-limiting embodiments or aspects, the transaction processing system 110 may generate a predicted and / or confidence score associated with a merchant transaction pattern (e.g., a pattern of values ​​in key fields of historical clearing records and / or authorization records) based on providing clearing records and one or more authorization records as input to a machine learning model. For example, the transaction processing system 110 may generate a predicted and / or confidence score associated with a merchant transaction pattern based on providing clearing records and one or more authorization records as input to a machine learning model, wherein the merchant transaction pattern is associated with one or more patterns in the merchant's historical transaction data (e.g., clearing delay patterns associated with time periods of clearing payment transactions, fraud transaction frequency patterns, etc.). In some non-limiting embodiments or aspects, transaction processing system 110 may update clearing records based on merchant transaction patterns and / or confidence scores. For example, transaction processing system 110 may update clearing records based on merchant transaction patterns and / or confidence scores included in the updated clearing records.

[0113] In some non-limiting embodiments or aspects, based on the transaction processing system 110 determining that a clearing record does not match one or more authorization records, the transaction processing system 110 may update the clearing record to provide an updated clearing record. For example, based on the transaction processing system 110 determining that a clearing record does not match one or more authorization records, the transaction processing system 110 may update the clearing record, and the transaction processing system 110 may retrieve a merchant identifier, an acquirer identifier, and / or transaction data associated with the payment transaction. In such examples, the merchant identifier, acquirer identifier, and transaction data of the clearing record may be associated with a clearing record that the transaction processing system 110 determines does not fully match or partially match one or more authorization records. In some non-limiting embodiments or aspects, the transaction processing system 110 may provide the merchant identifier, acquirer identifier, and transaction data as input to a machine learning model, the machine learning model being configured to determine a merchant transaction pattern associated with a time delay in receiving clearing records and authorization records. For example, the transaction processing system 110 may provide the merchant identifier, acquirer identifier, and transaction data as input to the machine learning model, and the transaction processing system 110 may generate an output including predictions based on providing the input to the machine learning model. For example, transaction processing system 110 can provide merchant identifiers, acquirer identifiers, and transaction data as inputs to a machine learning model, and transaction processing system 110 can generate an output including predictions based on the inputs provided to the machine learning model, the predictions being associated with estimated clearing delays (e.g., an estimated time period from the time of receiving the authorization record to the time of receiving the clearing record, an estimated time period associated with one or more parties making a payment transaction from the time of receiving the authorization record to the time of receiving the clearing record, etc.).

[0114] In some non-limiting embodiments or aspects, transaction processing system 110 may train a machine learning model configured to determine merchant transaction patterns associated with time delays in receiving clearing and authorization records. For example, transaction processing system 110 may train the machine learning model based on historical transaction data. Based on historical transaction data provided to the machine learning model, transaction processing system 110 can train the machine learning model. In such examples, historical transaction data may include data associated with historical authorization records, data associated with historical clearing records, and / or data associated with authorization volumes and / or clearing volumes, wherein the authorization volumes and / or clearing volumes are applicable to one or more parties conducting one or more payment transactions (e.g., one or more merchants, one or more acquirers, one or more issuers, etc.). In some non-limiting embodiments or aspects, historical transaction data may include data associated with the type of payment account involved in the payment transaction (e.g., credit account, debit account, etc.) (e.g., indicating the type of payment account), data associated with the payment channel involved in the payment transaction (e.g., indicating the payment channel) (e.g., indicators associated with face-to-face payment transactions, indicators associated with e-commerce (e.g., online) payment transactions, etc.), data associated with fraud risk scores (e.g., scores associated with determining whether a payment transaction is fraudulent or not), data associated with merchant type (e.g., indicators associated with transportation merchants, indicators associated with retail department store merchants, etc.), data associated with acquirer behavior (e.g., indicators of the acquirer processing payment transactions over a period of time, etc.), etc.

[0115] In some non-limiting embodiments or aspects, transaction processing system 110 may determine whether a clearing record is associated with a forced post-payment transaction. In one example, a clearing record associated with a forced post-payment transaction may include a clearing record that has been determined to be created based on the forced post-payment transaction (e.g., a clearing record created for clearing a transaction for which no prior authorized record has been created). Alternatively or additionally, transaction processing system 110 may determine whether a clearing record is associated with a forced post-payment transaction by comparing the output of a machine learning model with a threshold (e.g., a delay threshold associated with the amount of time associated with the forced post-payment transaction). If transaction processing system 110 determines that the output of the machine learning model (e.g., the estimated delay) meets the threshold, transaction processing system 110 may determine that the clearing record is not associated with the forced post-payment transaction. If transaction processing system 110 determines that the output of the machine learning model (e.g., the estimated delay) does not meet the threshold, transaction processing system 110 may determine that the clearing record is associated with the forced post-payment transaction.

[0116] Alternatively, based on a comparison between the probability of a clearing record being associated with a mandatory post-payment transaction and a confidence threshold (e.g., a threshold associated with the likelihood that a clearing record is associated with a mandatory post-payment transaction), the transaction processing system 110 can determine whether a clearing record is associated with a mandatory post-payment transaction. If the transaction processing system 110 determines that the probability of a clearing record being associated with a mandatory post-payment transaction meets the confidence threshold, the transaction processing system 110 can determine that the clearing record associated with the transaction data is suitable for the mandatory post-payment transaction. If the transaction processing system 110 determines that the probability of a clearing record being associated with a mandatory post-payment transaction does not meet the confidence threshold, the transaction processing system 110 can determine that the clearing record associated with the transaction data is not suitable for the mandatory post-payment transaction.

[0117] In some non-limiting embodiments or aspects, transaction processing system 110 may update the clearing record based on the determination that the clearing record does not match one or more authorization records and that the clearing record is not associated with a forced post-payment transaction. For example, transaction processing system 110 may update the clearing record based on the determination that the clearing record does not match one or more authorization records, and based on the determination that the clearing record is not associated with a forced post-payment transaction, the transaction processing system 110 includes an estimated clearing delay and a confidence score with the clearing record. In some non-limiting embodiments or aspects, transaction processing system 110 may also update the clearing record to include an estimated clearing delay, as described herein.

[0118] In some non-limiting embodiments or aspects, transaction processing system 110 may determine whether a clearing record is associated with an permitted mandatory post-payment transaction (e.g., a payment transaction that is a mandatory post-payment transaction and has not been identified as a fraudulent payment transaction). For example, transaction processing system 110 may provide a merchant identifier, an acquirer identifier, and transaction data as input to a machine learning model configured to classify clearing records as associated with either a legitimate or a non-permitted mandatory post-payment transaction. In such examples, based on the input provided to the machine learning model, transaction processing system 110 may generate an output. The output may include a prediction indicating whether the clearing record is associated with a permitted or non-permitted mandatory post-payment transaction. In some non-limiting embodiments or aspects, transaction processing system 110 may update clearing records based on the output of the machine learning model. For example, based on the output of the machine learning model, transaction processing system 110 may determine that the clearing record pertains to a non-permitted mandatory post-payment transaction, which could be a mandatory post-payment transaction that was not authorized by the payer due to the output of the machine learning model (e.g., an erroneous mandatory post-payment transaction, a fraudulent mandatory post-payment transaction, etc.). Transaction processing system 110 may update clearing records to include an indication that the clearing record is used for an unauthorized mandatory post-payment transaction. In some non-limiting embodiments or aspects, based on the output of a machine learning model, transaction processing system 110 may determine that the clearing record is for an authorized mandatory post-payment transaction, and transaction processing system 110 may update the clearing record to include an indication that the clearing record is for an authorized mandatory post-payment transaction. In some non-limiting embodiments or aspects, transaction processing system 110 may provide the updated clearing record to acquiring system 108. For example, based on transaction processing system 110 determining that the clearing record is not associated with an authorized mandatory post-payment transaction, transaction processing system 110 may provide the updated clearing record to acquiring system 108. In such examples, transaction processing system 110 may determine that the clearing record is not associated with an authorized mandatory post-payment transaction based on the output of a machine learning model.

[0119] In some non-limiting embodiments or aspects, the transaction processing system 110 may train a machine learning model. For example, the transaction processing system 110 may train a machine learning model based on historical transaction data provided to it. In such examples, historical transaction data may include data associated with historical authorization records; data associated with historical clearing records; data associated with a merchant's mandatory post-payment transactions indicating the frequency with which a merchant submits mandatory post-payment transactions; data associated with different merchants indicating the frequency with which different merchants submit mandatory post-payment transactions; data associated with a merchant indicating that a merchant has not submitted mandatory post-payment transactions; data associated with a merchant indicating that a merchant is associated with mandatory post-payment transactions with a high fraud rate (e.g., a mandatory post-payment transaction submitted by a merchant has a probability greater than a threshold probability of being fraudulent), etc.

[0120] like Figure 3 As shown, in step 310, process 300 may include transmitting updated clearing records. For example, transaction processing system 110 may transmit updated clearing records to acquiring system 108. In such an example, transaction processing system 110 may transmit updated clearing records to acquiring system 108, which transmits clearing records to transaction processing system 110. In some non-limiting embodiments or aspects, transaction processing system 110 may transmit updated clearing records to issuing system 112. For example, based on transaction processing system 110 determining that clearing records and / or one or more authorization records corresponding to clearing records are associated with issuing system 112, transaction processing system 110 may transmit updated clearing records to issuing system 112. In such an example, issuing system 112 may be involved in payment transactions associated with clearing records and / or one or more authorization records.

[0121] In some non-limiting embodiments or aspects, transaction processing system 110 may transmit updated clearing batch files to acquiring system 108. For example, transaction processing system 110 may transmit updated clearing batch files to acquiring system 108, where acquiring system 108 has previously transmitted clearing batch files to transaction processing system 110. In some non-limiting embodiments or aspects, transaction processing system 110 may transmit updated clearing batch files to issuing system 112. For example, based on transaction processing system 110 determining that a clearing batch file and / or one or more authorization records corresponding to clearing records included in the clearing batch file are associated with issuing system 112, transaction processing system 110 may transmit updated clearing batch files to issuing system 112. In such examples, issuing system 112 may be involved in payment transactions associated with one or more clearing records and / or one or more authorization records associated with the clearing batch file.

[0122] refer to Figure 4 The document provides an operation diagram for a process 400 for determining the correspondence of non-indexed records. The process may include acquiring system 108 integrating clearing records 405 for transmission to transaction processing system 110 of a transaction service provider. Transaction processing system 110 may receive clearing records 405 from acquiring system 108. In step 409, clearing records 405 may be normalized and / or enriched. Normalization may include reformatting the key fields of the clearing record according to a predetermined set of key field formats, for example, allowing the clearing record to be compared more accurately with authorized records. Enrichment may refer to changing and / or adding data to the clearing record. For example, transaction processing system 110 may normalize the key fields of clearing record 405, including but not limited to transaction amount, transaction ID, merchant name, etc. Alternatively or additionally, transaction processing system 110 may enrich clearing record 405 with additional information, including but not limited to providing a merchant identifier for one or more clearing records 405.

[0123] In step 413, a transaction matching process can be initiated. For example, transaction processing system 110 can initiate a transaction matching for each clearing record in a set of clearing records 405, for example, using a transaction matching module. In response to determining that a clearing record matches an authorization record (result A1), the transaction processing system may take no further action. Matching may include, for example, clearing records and authorization records having matching transaction identifiers, merchant identifiers, and / or transaction amounts. In response to determining that a clearing record partially matches at least one authorization record (result A2), transaction processing system 110 can execute a first process 417 of auxiliary transaction matching module 415, which can update the clearing record to match the authorization record. Reference Figure 5 The first process 417 is also disclosed. In response to determining that the clearing record does not match any authorization record (result A3), the transaction processing system 110 can execute the second process 419 of the auxiliary transaction matching module 415, which can update the clearing record to match the authorization record. (See reference) Figure 6 The second process, 419, was also disclosed.

[0124] In outputs B1, B2, and B3, matching clearing records and authorization records may be provided, for example, by transaction processing system 110. B2 and B3 may include updated clearing records matching authorization records with confidence scores riched by a machine learning model used to establish a match between a given clearing record and an authorization record. Transaction processing system 110 may merge outputs B2 and B3 to form a merged output C1 associated with the clearing records and authorization records matched using auxiliary transaction matching module 415. Second process 419 may further output clearing records identifiable by no matching authorization records in output C2. Transaction processing system 110 may merge all outputs (e.g., outputs C1 and C2) of processes 417 and 419 of auxiliary transaction matching module 415, including merging with clearing records and authorization records that match in output B1 without further comparative analysis. Output D may include a set of compiled clearing records, which includes outputs B1, C1, and C2. Transaction processing system 110 may then transmit output D to issuer system 112.

[0125] refer to Figure 5 An operational diagram for determining the correspondence of a non-indexed record is provided. For example, the first process 417 can be performed when one or more clearing records 405 are identified as partially matched with one or more authorization records (e.g., one or more key fields, but not all key fields, include the same value). In some non-limiting embodiments or aspects, one or more functions described with respect to the first process 417 can be performed by the transaction processing system 110 (e.g., entirely, partially, etc.). In some non-limiting embodiments or aspects, one or more steps of the first process 417 can be performed by another device or group of devices (e.g., user device 102, merchant system 104, payment gateway system 106, acquiring system 108, and / or issuing system 112) separate from and / or including the transaction processing system 110 (e.g., entirely, partially, etc.).

[0126] In step 503, it can be determined whether only the transaction amount in the clearing record does not match the authorization record. For example, the transaction processing system 110 can determine whether the clearing record matches the authorization record in all key fields except the transaction amount. If the clearing record matches the authorization record in all key fields except the transaction amount, step 505 can be executed. If the clearing record does not match the authorization record in all key fields except the transaction amount, step 509 can be executed.

[0127] In step 505, it can be determined whether a partial reversal exists. For example, transaction processing system 110 can determine whether the difference in transaction amount between a clearing record that partially matches an authorization record is due to a partial reversal of the transaction amount. A partial reversal may include a transaction where the clearing record amount is less than the authorization record amount, and therefore the payer's payment amount is less than the original authorized amount. Determining a partial reversal may include comparing the clearing record amount with the authorization record amount to determine whether the clearing record amount is less than the authorization record amount. If the clearing record amount is less than the authorization record amount, indicating a partial reversal, step 507 can be executed.

[0128] In step 507, the original transaction amount data can be added to the partially matching clearing record. For example, transaction processing system 110 can update the partially matching clearing record to produce an updated clearing record, which may include data on the original transaction amount authorized prior to partial revocation associated with the difference in transaction amount. In some non-limiting embodiments or aspects, the added data may be included in an existing clearing record key field or an additional clearing record key field.

[0129] In step 509, it can be determined whether only the transaction identifier of the clearing record does not match the given authorization record. For example, the transaction processing system 110 can determine whether the clearing record matches the authorization record in all key fields except the transaction identifier. If the clearing record matches the authorization record in all key fields except the transaction identifier, step 511 can be executed. If the clearing record does not match the authorization record in all key fields except the transaction identifier, step 513 can be executed.

[0130] In step 511, the original transaction identifier can be added to the partially matching clearing record. For example, by including the transaction identifier of the authorization record in the clearing record data, the transaction processing system 110 can update the clearing record that matches the authorization record in all key fields except the transaction identifier to produce an updated clearing record. In some non-limiting embodiments or aspects, the added data may be included in existing clearing record key fields or additional clearing record key fields.

[0131] In step 513, it can be evaluated whether each remaining key field of the clearing record does not match the authorization record. For example, transaction processing system 110 can determine whether the clearing record partially matches the authorization record but differs in more than one key field. If multiple key fields do not match between the clearing record and the authorization record, step 515 can be performed.

[0132] In step 515, a machine learning model can be used to determine the discrepancy and confidence score of the clearing record. For example, for each clearing record processed in the first process 417, the transaction processing system 110 can generate a discrepancy limit and a confidence score based on the generated discrepancy limit. The discrepancy limit can be generated from a machine learning model trained with historical authorization records and clearing records and based on inputting the merchant and / or acquirer identifier associated with the analyzed clearing record into the machine learning model. The discrepancy limit can be the maximum or minimum discrepancy value in the key fields of the clearing record and / or authorization record. In some non-limiting embodiments or aspects, the discrepancy limit can be based on the historical (e.g., average, median, etc. of past values) difference (e.g., 5%) between the transaction amount of a given merchant's clearing record and authorization record. In some non-limiting embodiments or aspects, the discrepancy limit can be based on the historical difference in the time (e.g., 7 days) between the clearing record and authorization record transmitted from the acquirer system. Based on the generated discrepancy limit of the clearing record, the confidence score of the clearing record can be generated by comparing (i) the difference between the value of the key field of the clearing record and the value of the same key field of the authorization record with (ii) the generated discrepancy limit. The confidence score can be a value representing the degree to which the difference between the liquidation record value and the authorization record value is within the difference limit. A high confidence score can be assigned to a low difference that is within the difference limit. A low confidence score can be assigned to a high difference that is outside the difference limit.

[0133] In step 517, the settlement records of steps 507, 511, and 515 can be merged. For example, transaction processing system 110 can merge the settlement records of steps 507, 511, and 515 to form the output of the first process 417.

[0134] refer to Figure 6 An operational diagram of a second process 419 for determining the correspondence of non-indexed records is provided. For example, the second process 419 may be performed when one or more clearing records 405 compare one or more authorization records and do not identify a match. In some non-limiting embodiments or aspects, one or more functions described regarding the second process 419 may be performed by the transaction processing system 110 (e.g., entirely, partially, etc.). In some non-limiting embodiments or aspects, one or more steps of the second process 419 may be performed by another device or group of devices (e.g., user device 102, merchant system 104, payment gateway system 106, acquiring system 108, and / or issuing system 112) separate from and / or including the transaction processing system 110 (e.g., entirely, partially, etc.).

[0135] In step 603, for each clearing record for which no match is identified, the merchant identifier, acquirer identifier, and transaction data of the clearing record can be identified. For example, the transaction processing system 110 can identify, for example, the merchant identifier, acquirer identifier, and transaction data associated with the transaction of the clearing record stored in the key field of the clearing record.

[0136] In step 605, an estimated clearing delay and confidence score can be derived from the output of a machine learning model that is configured to determine merchant transaction patterns associated with the time delays in receiving clearing and authorization records. For example, transaction processing system 110 can operate a machine learning model programmed and / or configured to be trained on historical transaction data 607 (e.g., authorization record data, clearing record data, etc.) to determine a merchant's transaction patterns. Given inputs of a merchant identifier, an acquirer identifier, and / or other transaction data for the clearing record, the machine learning model can generate an estimated time delay associated with the merchant initiating the clearing record (e.g., the delay from receiving the clearing record to receiving the authorization record) and a confidence score for mismatched clearing records. The confidence score may include a value that indicates, at least in part, the probability that the clearing record is a forced post-payment transaction based on the estimated time delay. A high confidence score may indicate a high probability that the clearing record is not associated with a forced post-payment transaction. A high confidence score may be due to the clearing record being associated with a merchant with a high estimated clearing time delay, which may indicate that a matching authorization record was not identified due to the high delay. A low confidence score indicates a low probability that a clearing record is associated with a forced post-payment transaction. A low confidence score may be derived from associating a clearing record with a merchant having a low estimated clearing time delay, which could indicate that a matching authorization record may not exist, as a matching authorization record would be more likely to be identified due to the low delay.

[0137] In some non-limiting embodiments or aspects, historical transaction data 607 may include data associated with the type of payment account involved in the payment transaction (e.g., credit account, debit account, etc.) (e.g., indicating the type of payment account), data associated with the payment channel involved in the payment transaction (e.g., indicating the payment channel) (e.g., indicators associated with face-to-face payment transactions, indicators associated with e-commerce (e.g., online) payment transactions, etc.), data associated with fraud risk scores (e.g., scores associated with determining whether a payment transaction is fraudulent or not), data associated with merchant type (e.g., indicators associated with transportation merchants, indicators associated with retail department store merchants, etc.), data associated with acquirer behavior (e.g., indicators of the acquirer processing payment transactions over a period of time, etc.), etc. With further examples, the machine learning model can identify merchant transaction patterns based on the aforementioned historical transaction data 607, such as: debit transaction clearing may be faster than credit transaction clearing; face-to-face transaction clearing may be faster than e-commerce transaction clearing; low-risk transaction clearing may be faster than high-risk transaction clearing; transportation merchant clearing may be faster than retail department store transaction clearing; some acquirers may clear faster than other acquirers; and so on.

[0138] Additionally, in step 605, the machine learning model can generate a prediction of the potential delay between authorization and clearing for the merchant after training on historical transaction data 607. The machine learning model can continuously regenerate estimates (e.g., retrain and re-execute the model) as additional data becomes available and is added to the historical transaction data 607 that can be used to train the machine learning model.

[0139] In step 609, it can be determined whether the output confidence score of step 605 meets (e.g., meets and / or exceeds) a predetermined threshold. For example, the transaction processing system 110 can be programmed and / or configured to have a predetermined threshold confidence level. The predetermined threshold confidence level can be a higher value (e.g., greater than 50 on a scale of 0 to 100) that makes false alarms less frequent and / or minimized. The transaction processing system 110 can determine whether the confidence score of the clearing record for each analyzed clearing record meets the predetermined threshold. If the generated confidence score of the clearing record meets the predetermined threshold, step 611 can be executed. If the generated confidence score of the clearing record does not meet the predetermined threshold, step 613 can be executed.

[0140] In step 611, the estimated clearing delay and confidence score can be output from the second process 419. For example, transaction processing system 110 can output the estimated clearing delay and confidence score for each clearing record having a confidence score that meets the predetermined threshold in step 609. In some non-limiting embodiments or aspects, transaction processing system 110 can generate updated clearing records by modifying and / or appending key fields to include the estimated clearing delay and confidence score.

[0141] In step 613, a machine learning model configured to classify clearing records as associated with legitimate or disallowed forced post-payment transactions can determine whether a clearing record with a confidence score that does not meet a predetermined threshold is associated with a legitimate forced post-payment transaction. For example, transaction processing system 110 can execute a machine learning model trained on historical transaction data 607 and configured to determine whether the merchant and / or acquirer has a historical frequency of sending forced post-payment transactions, thereby indicating the likelihood of performing this operation in relation to the clearing record. In some non-limiting embodiments or aspects, the model features of the machine learning model may include, but are not limited to: whether the merchant regularly submits forced post-payment transactions (which may indicate legitimate transaction behavior), similarly, whether the merchant regularly submits forced post-payment transactions (which may indicate legitimate transaction behavior), whether the merchant has a high rate of fraudulent forced post-payment transactions (which may indicate disallowed transaction behavior), etc. After training on historical transaction data 607, in step 613, the machine learning model can receive input from clearing records and classify the clearing records as associated with legitimate or disallowed forced post-payment transactions.

[0142] For clearing records that may be associated with legitimate forced post-payment transactions, in step 615, the machine learning model can return an indicator that the transaction associated with the clearing record is a legitimate forced post-payment transaction. For clearing records that may be associated with disallowed forced post-payment transactions, in step 617, the machine learning model can return an indicator that the transaction associated with the clearing record is a disallowed forced post-payment transaction. In some non-limiting embodiments or aspects, the transaction processing system 110 can generate updated clearing records by modifying and / or appending key fields to include indicators of clearing records associated with legitimate or disallowed forced post-payment transactions. The clearing records from steps 611, 615, and 617 can then be combined to form the aggregate output of the second process 419.

[0143] Alternatively, an updated clearing record, including an indicator of a clearing record associated with an unauthorized mandatory post-payment transaction, may be remedied by the transaction processing system 110 by transmitting it to the acquiring system 108, rather than being transmitted to the issuing system 112 for transaction posting. In such an example, clearing records associated with unauthorized mandatory post-payment transactions may be removed and / or excluded (e.g., not merged with other clearing records) from an updated clearing batch file that can be transmitted to the issuing system 112. Alternatively, the acquiring system 108 may receive updated clearing records returned with an indicator indicating that the clearing record is associated with an unauthorized mandatory post-payment transaction that is actually legitimate. If the associated transaction is legitimate, the acquiring system 108 may check the legitimacy of the clearing record and resubmit the authorization request for the associated transaction by sending an authorization record and then sending a new clearing record.

[0144] Although the above-described methods, systems, and computer program products have been described in detail for illustrative purposes based on embodiments or aspects currently considered most practical and preferred, it should be understood that such details are for illustrative purposes only, and this disclosure is not limited to the described embodiments or aspects; rather, this disclosure is intended to cover modifications and equivalent arrangements that fall within the spirit and scope of the appended claims. For example, it should be understood that this disclosure contemplates, as far as possible, that one or more features of any embodiment or aspect may be combined with one or more features of any other embodiment or aspect.

Claims

1. A computer-implemented method, comprising: A clearing record, including at least one key field, is received by at least one processor. The clearing record is associated with one or more payment transactions completed in a payment transaction processing network. The clearing record refers to a transmitted data object sent from the acquiring system to the transaction processing system. The data object is transmitted to the issuing system and is in the format necessary for the clearing transaction. At least one processor compares a value associated with a first key field of the clearing record with a value associated with a first key field of one or more authorization records, the one or more authorization records being associated with one or more authorized payment transactions in the payment transaction processing network, wherein the first key field of the clearing record corresponds to the first key field of the one or more authorization records, and wherein the one or more authorization records are associated with an authorization request for a payment transaction in the one or more payment transactions; Based on a comparison of the value associated with the first key field of the liquidation record and the value associated with the first key field of the one or more authorization records, at least one processor determines that the liquidation record corresponds to an authorization record among the one or more authorization records; Based on the determination that the liquidation record corresponds to the authorization record, at least one processor generates an updated liquidation record; as well as The updated liquidation record is transmitted by at least one processor.

2. The computer-implemented method of claim 1, wherein receiving the clearing record associated with the one or more payment transactions comprises: A clearing batch file containing multiple clearing records of multiple payment transactions is received by at least one processor. The computer-implemented method further includes: At least one processor normalizes one or more of the plurality of liquidation records in the liquidation batch file based on a liquidation record template associated with the issuer's system. When normalizing the one or more liquidation records in the liquidation batch file, the at least one processor converts one or more values ​​associated with one or more key fields of the one or more liquidation records into one or more updated values.

3. The computer-implemented method according to claim 1, further comprising: At least one processor compares the value associated with the second key field of the liquidation record with the value associated with the second key field of the one or more authorization records, wherein the second key field of the liquidation record corresponds to the second key field of the one or more authorization records. The determination that the liquidation record corresponds to the authorization record among the one or more authorization records includes: Based on a comparison of the value associated with the second key field of the liquidation record and the value associated with the second key field of the one or more authorization records, The liquidation record is determined by at least one processor to correspond to the authorization record among the one or more authorization records; The first key field is associated with at least one of the transaction identifier, transaction amount, and payment account type, and The second key field is associated with another of at least one of the transaction identifier, the transaction amount, and the payment account type.

4. The computer-implemented method of claim 3, wherein determining that the liquidation record corresponds to the authorization record among the one or more authorization records comprises: At least one processor determines that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record; as well as At least one processor determines that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record. The computer-implemented method further includes: Based on the determination that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record, at least one processor determines that the liquidation record partially matches the authorization record.

5. The computer-implemented method of claim 3, wherein determining that the liquidation record corresponds to the authorization record among the one or more authorization records comprises: At least one processor determines that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record; as well as At least one processor determines that the value associated with the second key field of the liquidation record matches the value associated with the second key field of the authorization record. The computer-implemented method further includes: Based on the determination that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the liquidation record matches the value associated with the second key field of the authorization record, at least one processor determines that the liquidation record matches the authorization record.

6. The computer-implemented method of claim 3, wherein determining that the liquidation record corresponds to the authorization record among the one or more authorization records comprises: At least one processor determines that the value associated with the first key field of the liquidation record does not match the value associated with the first key field of the authorization record; as well as At least one processor determines that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record. The computer-implemented method further includes: Based on the determination that the value associated with the first key field of the liquidation record does not match the value associated with the first key field of the authorization record, and that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record, at least one processor determines that the liquidation record does not match the authorization record.

7. The computer-implemented method of claim 1, wherein generating the updated liquidation record comprises: The liquidation record and the authorization record are provided as input to the machine learning model by at least one processor; Based on providing the liquidation record and the authorization record as input to the machine learning model, at least one processor generates a prediction associated with a confidence score that matches the liquidation record with the authorization record; as well as The liquidation record is updated by at least one processor based on the confidence score.

8. The computer-implemented method of claim 7, wherein updating the liquidation record based on the confidence score comprises at least one of the following: The confidence score is appended to the liquidation record by at least one processor; The initial transaction amount of the authorization record is appended to the settlement record by at least one processor; as well as The transaction identifier of the authorization record is appended to the settlement record by at least one processor.

9. The computer-implemented method according to claim 2, further comprising: An updated liquidation batch file is generated by at least one processor based on the liquidation batch file and the updated liquidation record; The updated clearing records transmitted include: The updated liquidation batch file is transferred to the issuer system by at least one processor.

10. The computer-implemented method of claim 6, wherein generating the updated liquidation record based on determining that the liquidation record corresponds to the authorization record comprises: The liquidation records and the one or more authorization records are provided to the machine learning model by at least one processor; Based on providing the liquidation records and the one or more authorization records to the machine learning model, at least one processor generates predictions associated with merchant transaction patterns and confidence scores; as well as The clearing record is updated by at least one processor based on the merchant's transaction pattern and the confidence score.

11. A system comprising a server, the server including at least one processor, the at least one processor being programmed and / or configured to: Receive a clearing record including at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network, wherein the clearing record refers to a transmitted data object sent from the acquiring system to the transaction processing system, the data object being transmitted to the issuing system and in the format necessary for the clearing transaction; The value associated with the first key field of the clearing record is compared with the value associated with the first key field of one or more authorization records, which are associated with one or more authorized payment transactions in the payment transaction processing network, wherein the first key field of the clearing record corresponds to the first key field of the one or more authorization records, and wherein the one or more authorization records are associated with an authorization request for a payment transaction in the one or more payment transactions; Based on a comparison of the value associated with the first key field of the liquidation record and the value associated with the first key field of the one or more authorization records, it is determined that the liquidation record corresponds to an authorization record among the one or more authorization records; Based on the determination that the liquidation record corresponds to the authorization record, an updated liquidation record is generated; as well as Transmit the updated liquidation record.

12. The system of claim 11, wherein receiving the clearing record associated with the one or more payment transactions comprises: Receive clearing batch files containing multiple clearing records for multiple payment transactions. The at least one processor is further programmed and / or configured to: One or more liquidation records from the plurality of liquidation records in the liquidation batch file are normalized based on a liquidation record template associated with the issuer's system. When normalizing the one or more liquidation records in the liquidation batch file, the at least one processor converts one or more values ​​associated with one or more key fields of the one or more liquidation records into one or more updated values.

13. The system of claim 11, wherein the at least one processor is further programmed and / or configured to: The value associated with the second key field of the liquidation record is compared with the value associated with the second key field of the one or more authorization records, wherein the second key field of the liquidation record corresponds to the second key field of the one or more authorization records. The determination that the liquidation record corresponds to the authorization record among the one or more authorization records includes: Based on a comparison of the value associated with the second key field of the liquidation record and the value associated with the second key field of the one or more authorization records, it is determined that the liquidation record corresponds to the authorization record among the one or more authorization records; The first key field is associated with at least one of the transaction identifier, transaction amount, and payment account type, and The second key field is associated with another of at least one of the transaction identifier, the transaction amount, and the payment account type.

14. The system of claim 13, wherein determining that the liquidation record corresponds to the authorization record among the one or more authorization records comprises: Determine that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record; as well as It is determined that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record. The at least one processor is further programmed and / or configured to: Based on the determination that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record, it is determined that the liquidation record partially matches the authorization record.

15. The system of claim 11, wherein generating the updated liquidation record comprises: The liquidation records and the authorization records are provided as input to the machine learning model; Based on providing the liquidation record and the authorization record as input to the machine learning model, a prediction is generated that is associated with the confidence score of the authorization record that matches the liquidation record; as well as The liquidation record is updated based on the confidence score.

16. A computer program product comprising a non-transitory computer-readable medium storing program instructions configured to cause at least one processor to perform the following operations: Receive a clearing record including at least one key field, the clearing record being associated with one or more payment transactions completed in a payment transaction processing network, wherein the clearing record refers to a transmitted data object sent from the acquiring system to the transaction processing system, the data object being transmitted to the issuing system and in the format necessary for the clearing transaction; The value associated with the first key field of the clearing record is compared with the value associated with the first key field of one or more authorization records, which are associated with one or more authorized payment transactions in the payment transaction processing network, wherein the first key field of the clearing record corresponds to the first key field of the one or more authorization records, and wherein the one or more authorization records are associated with an authorization request for a payment transaction in the one or more payment transactions; Based on a comparison of the value associated with the first key field of the liquidation record and the value associated with the first key field of the one or more authorization records, it is determined that the liquidation record corresponds to an authorization record among the one or more authorization records; Based on the determination that the liquidation record corresponds to the authorization record, an updated liquidation record is generated; as well as Transmit the updated liquidation record.

17. The computer program product of claim 16, wherein receiving the clearing record associated with the one or more payment transactions comprises: Receive clearing batch files containing multiple clearing records for multiple payment transactions. The program instructions are further configured to cause the at least one processor to perform the following operations: One or more liquidation records from the plurality of liquidation records in the liquidation batch file are normalized based on a liquidation record template associated with the issuer's system. When normalizing the one or more liquidation records in the liquidation batch file, the at least one processor converts one or more values ​​associated with one or more key fields of the one or more liquidation records into one or more updated values.

18. The computer program product of claim 16, wherein the program instructions are further configured to cause the at least one processor to perform the following operations: The value associated with the second key field of the liquidation record is compared with the value associated with the second key field of the one or more authorization records, wherein the second key field of the liquidation record corresponds to the second key field of the one or more authorization records. The determination that the liquidation record corresponds to the authorization record among the one or more authorization records includes: Based on a comparison of the value associated with the second key field of the liquidation record and the value associated with the second key field of the one or more authorization records, it is determined that the liquidation record corresponds to the authorization record among the one or more authorization records; The first key field is associated with at least one of the transaction identifier, transaction amount, and payment account type, and The second key field is associated with another of at least one of the transaction identifier, the transaction amount, and the payment account type.

19. The computer program product of claim 18, wherein determining that the liquidation record corresponds to the authorization record among the one or more authorization records comprises: Determine that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record; as well as It is determined that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record. The program instructions are further configured to cause the at least one processor to perform the following operations: Based on the determination that the value associated with the first key field of the liquidation record matches the value associated with the first key field of the authorization record and that the value associated with the second key field of the liquidation record does not match the value associated with the second key field of the authorization record, it is determined that the liquidation record partially matches the authorization record.

20. The computer program product of claim 16, wherein generating the updated liquidation record comprises: The liquidation records and the authorization records are provided as input to the machine learning model; Based on providing the liquidation record and the authorization record as input to the machine learning model, a prediction is generated that is associated with the confidence score of the authorization record that matches the liquidation record; as well as The liquidation record is updated based on the confidence score.

Images