Systems, methods, and computer program products for generating code to retrieve aggregated data for machine learning models

Abstract

A system is provided that includes at least one processor programmed or configured to: receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model; generate a code generation template based on the data associated with the one or more input parameters of the machine learning model included in the XML file, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregation of an account of a user; and generate an executable code file based on the code generation template, wherein the executable code file includes instructions that, when executed by at least one processor, cause the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the account of the user. A method and computer program product are also provided.

Description

Technical Field

[0001] This disclosure generally relates to machine learning models, and in some non-limiting aspects or embodiments, to systems, methods, and computer program products for generating transaction aggregates associated with predictions of transactions that can be used with machine learning models. Background Technology

[0002] Machine learning can be a field of computer science that uses statistical techniques to enable computer systems to learn from data (e.g., progressively improve performance) for tasks without explicitly programming the computer system to perform those tasks. In some cases, machine learning models can be developed for datasets that can perform tasks related to said dataset (e.g., tasks associated with prediction).

[0003] In some cases, machine learning models, such as predictive machine learning models, can be used to make predictions associated with risk or opportunity. Predictive machine learning models can be used to analyze the relationship between a unit's performance and one or more known features of the unit based on data associated with that unit.

[0004] In some examples, predictive machine learning models may require inputs that include features based on data aggregations (e.g., aggregated data). For instance, a predictive machine learning model might require inputs that include features based on aggregated data computed in real time. However, computed aggregated data in real time can be resource-intensive and may require a significant amount of time to compute.

[0005] Furthermore, a machine learning model developed for one dataset may not be applicable to a particular problem on another dataset. For example, a machine learning model developed for a first dataset associated with a specific geographic region and / or demographics may not be applicable to a specific prediction on a second dataset associated with a different geographic region and / or demographics. This can lead to the creation of numerous machine learning models for each dataset, and also the creation of large amounts of data for each machine learning model. Summary of the Invention

[0006] Therefore, systems, methods, and computer program products for generating code to retrieve aggregated data for machine learning models are disclosed.

[0007] According to some non-limiting aspects or embodiments, a system is provided, comprising: at least one processor programmed or configured to: receive an Extensible Markup Language (XML) data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model; generate a code generation template based on the data associated with the one or more input parameters of the machine learning model included in the XML file, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account, wherein the one or more parameters of the transaction aggregate of the user's account are based on one or more parameters relating to multiple payment transactions of the user's account; and generate an executable code file based on the code generation template, wherein the executable code file includes instructions that, when executed by the at least one processor, cause the at least one processor to retrieve transaction aggregate data associated with the transaction aggregate of the user's account.

[0008] According to some non-limiting aspects or embodiments, a computer-implemented method is provided, comprising: receiving a data file using at least one processor, wherein the data file includes data associated with one or more input parameters of a machine learning model; generating a code generation template using at least one processor based on the data associated with the one or more input parameters of the machine learning model included in the data file, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account; and generating an executable code file using at least one processor based on the code generation template, wherein the executable code file includes instructions that, when executed by at least one processor, cause the at least one processor to retrieve transaction aggregate data associated with the transaction aggregate of the user's account.

[0009] According to some non-limiting aspects or embodiments, a computer program product is provided, comprising: at least one non-transitory computer-readable medium, the at least one non-transitory computer-readable medium including one or more instructions, the one or more instructions, when executed by at least one processor, causing the at least one processor to: receive a data file associated with a machine learning model; generate a code generation template based on receiving the data file associated with the machine learning model, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregation of a user's account, wherein the one or more parameters of the transaction aggregation of the user's account are based on one or more parameters of a plurality of payment transactions involving the user's account; and generate an executable code file based on the code generation template, wherein the executable code file includes instructions, the instructions, when executed by the at least one processor, causing the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account.

[0010] Further non-limiting aspects or embodiments are set forth in the following numbered clauses:

[0011] Clause 1: A system comprising: at least one processor programmed or configured to: receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model; generate a code generation template based on the data associated with the one or more input parameters of the machine learning model included in the XML file, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account, wherein the one or more parameters of the transaction aggregate of the user's account are based on one or more parameters relating to a plurality of payment transactions of the user's account; and generate an executable code file based on the code generation template, wherein the executable code file includes instructions that, when executed by the at least one processor, cause the at least one processor to retrieve transaction aggregate data associated with the transaction aggregate of the user's account.

[0012] Clause 2: The system according to Clause 1, wherein the code generation template includes a template for an SQL query, and wherein the template for the SQL query includes one or more keys associated with one or more parameters of the transaction aggregation of the user's account.

[0013] Clause 3: The system according to Clause 1 or 2, wherein, when the executable code file is generated, the at least one processor is programmed or configured to: generate the executable code file, which, when executed by the at least one processor, causes the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database among a plurality of databases.

[0014] Clause 4: The system according to any one of Clauses 1 to 3, wherein the at least one processor is further programmed or configured to: receive from a client device a request for a risk assessment determination of a payment transaction involving the user's account; retrieve first transaction aggregate data associated with a first transaction aggregate of the user's account; and use the first transaction aggregate data associated with the first transaction aggregate of the user's account as input to the machine learning model to determine a risk assessment score associated with the payment transaction involving the user's account.

[0015] Clause 5: The system according to any one of Clauses 1 to 4, wherein, when retrieving first transaction aggregate data associated with the first transaction aggregate of the user's account, the at least one processor is programmed or configured to: retrieve short-term aggregate data associated with the first transaction aggregate of the user's account from a short-term database; and retrieve long-term aggregate data associated with the first transaction aggregate of the user's account from a long-term database.

[0016] Clause 6: A system according to any one of Clauses 1 to 5, wherein, when retrieving the first transaction aggregate data associated with the first transaction aggregate of the user's account, the at least one processor is programmed or configured to: retrieve the first transaction aggregate data associated with the first transaction aggregate of the user's account from one or more databases based on executing the executable code file.

[0017] Clause 7: A system according to any one of Clauses 1 to 6, wherein, upon receiving the XML file, the at least one processor is programmed or configured to: receive the XML file from a client device via a web application, and wherein the data associated with one or more input parameters of the machine learning model is based on data received via the web application.

[0018] Clause 8: A computer-implemented method comprising: receiving a data file using at least one processor, wherein the data file includes data associated with one or more input parameters of a machine learning model; generating a code generation template using at least one processor based on the data associated with the one or more input parameters of the machine learning model included in the data file, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account; and generating an executable code file using at least one processor based on the code generation template, wherein the executable code file includes instructions that, when executed by at least one processor, cause the at least one processor to retrieve transaction aggregate data associated with the transaction aggregate of the user's account.

[0019] Clause 9: The method according to Clause 8, wherein the file that generates the executable code file comprises: generating the executable code file, which, when executed by at least one processor, causes at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database of a plurality of databases.

[0020] Clause 10: The method according to Clause 8 or 9 further includes: receiving from a client device a request for a risk assessment determination of payment transactions involving the user's account; retrieving first transaction aggregation data associated with a first transaction aggregation of the user's account; and using the first transaction aggregation data associated with the first transaction aggregation of the user's account as input to the machine learning model to determine a risk assessment score associated with the payment transactions involving the user's account.

[0021] Clause 11: The method according to any one of Clauses 8 to 10, wherein retrieving first transaction aggregate data associated with the first transaction aggregate of the user's account comprises: retrieving short-term aggregate data associated with the first transaction aggregate of the user's account from a short-term database; and retrieving long-term aggregate data associated with the first transaction aggregate of the user's account from a long-term database.

[0022] Clause 12: The method according to any one of Clauses 8 to 11, wherein the first transaction aggregate data associated with the first transaction aggregate of the user's account is retrieved, and the at least one processor is programmed or configured to: retrieve the first transaction aggregate data associated with the first transaction aggregate of the user's account from one or more databases based on the execution of the executable code file.

[0023] Clause 13: The method according to any one of Clauses 8 to 12 further includes: determining whether the risk assessment score associated with the payment transaction involving the user's account meets a risk assessment threshold; and performing an operation based on the determination that the risk assessment score associated with the payment transaction involving the user's account meets the risk assessment threshold.

[0024] Clause 14: The method according to any one of Clauses 8 to 13, wherein receiving the data file comprises: receiving an XML file from a client device via a web application, and wherein the data associated with one or more input parameters of the machine learning model is based on data received via the web application.

[0025] Clause 15: A computer program product comprising at least one non-transitory computer-readable medium, the at least one non-transitory computer-readable medium comprising one or more instructions, the one or more instructions, when executed by at least one processor, causing the at least one processor to: receive a data file associated with a machine learning model; generate a code generation template based on receiving the data file associated with the machine learning model, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account, wherein the one or more parameters of the transaction aggregate of the user's account are based on one or more parameters relating to a plurality of payment transactions of the user's account; and generate an executable code file based on the code generation template, wherein the executable code file includes instructions, the instructions, when executed by the at least one processor, causing the at least one processor to retrieve transaction aggregate data associated with the transaction aggregate of the user's account.

[0026] Clause 16: The computer program product pursuant to Clause 15, wherein the code generation template includes a template for an SQL query, and wherein the template for the SQL query includes one or more keys associated with one or more parameters of the transaction aggregation of the user's account.

[0027] Clause 17: A computer program product according to Clause 15 or 16, wherein one or more instructions of a file that cause the at least one processor to generate the executable code file cause the at least one processor to: generate the executable code file, which, when executed by the at least one processor, causes the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database of a plurality of databases.

[0028] Clause 18: A computer program product according to any one of Clauses 15 to 17, wherein one or more instructions further cause the at least one processor to: receive from a client device a request for a risk assessment determination of payment transactions involving the user's account; retrieve first transaction aggregation data associated with a first transaction aggregation of the user's account; and use the first transaction aggregation data associated with the first transaction aggregation of the user's account as input to the machine learning model to determine a risk assessment score associated with the payment transactions involving the user's account.

[0029] Clause 19: A computer program product according to any one of Clauses 15 to 18, wherein one or more instructions causing the at least one processor to retrieve first transaction aggregate data associated with the first transaction aggregate of the user's account cause the at least one processor to: retrieve short-term aggregate data associated with the first transaction aggregate of the user's account from a short-term database; and retrieve long-term aggregate data associated with the first transaction aggregate of the user's account from a long-term database.

[0030] Clause 20: A computer program product according to any one of Clauses 15 to 19, wherein the one or more instructions that cause the at least one processor to receive the XML file cause the at least one processor to: receive the XML file from a client device via a web application, and wherein the data associated with one or more input parameters of the machine learning model is based on data received via the web application.

[0031] The operational methods and manufacturing economics of these and other features and characteristics of this disclosure, as well as the combinations of related structural elements and parts, will become more apparent after considering the following description and appended claims with reference to the accompanying drawings, all of which form part of this specification, wherein similar reference numerals in the drawings indicate corresponding parts. However, it should be clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to be construed as limiting the scope of this disclosure. Unless the context clearly requires otherwise, the singular forms “a” and “described” as used in this specification and claims include plural indicators. Attached Figure Description

[0032] Additional advantages and details of the non-limiting aspects or embodiments are explained in more detail below with reference to exemplary embodiments illustrated in the accompanying diagrams, in which:

[0033] Figure 1 A diagram is a non-limiting aspect or embodiment of an environment in which the apparatus, system, method and / or product described herein may be implemented;

[0034] Figure 2 yes Figure 1 A diagram of a non-limiting aspect or embodiment of one or more devices and / or one or more systems components;

[0035] Figure 3 A flowchart of a non-limiting aspect or embodiment of a process for generating code to retrieve aggregated data for a machine learning model; and

[0036] Figures 4A-4E This is a diagram of a non-limiting embodiment of a process for generating code to retrieve aggregated data from a machine learning model. Detailed Implementation

[0037] For descriptive purposes, the terms “end,” “upper,” “lower,” “right,” “left,” “vertical,” “horizontal,” “top,” “bottom,” “lateral,” “longitudinal,” and their derivatives are intended to refer to the orientation of this disclosure as shown in the accompanying drawings. However, it should be understood that this disclosure may take various alternative variations and sequences of steps, except where explicitly specified otherwise. It should also be understood that the specific apparatus and processes illustrated in the drawings and described in the following description are merely exemplary embodiments or aspects of this disclosure. Therefore, unless otherwise indicated, specific dimensions and other physical characteristics associated with the embodiments or aspects of the embodiments disclosed herein should not be considered limiting.

[0038] The terms "aspects," "components," "elements," "elements," "structures," "actions," "steps," "functions," and "instructions" used herein should not be construed as critical or essential unless explicitly stated otherwise. Furthermore, as used herein, the article "a" is intended to include one or more items and may be used interchangeably with "one or more" and "at least one." Additionally, as used herein, the term "set" is intended to include one or more items (e.g., related items, unrelated items, combinations of related and unrelated items, etc.) and may be used interchangeably with "one or more" or "at least one." Where only one item is desired, the term "a" or similar language is used. Furthermore, as used herein, the terms "having" and similar expressions are intended to be open-ended terms. Additionally, unless explicitly stated otherwise, the phrase "based on" is intended to mean "at least partially based on."

[0039] As used herein, the terms "communication" and "transmission" can refer to the receipt, acceptance, sending, transmission, provisioning, etc., of information (e.g., data, signals, messages, instructions, commands, etc.). Communication between one unit (e.g., a device, system, component of a device or system, combination thereof, etc.) and another unit means that the first unit is able to receive information directly or indirectly from and / or send (e.g., transmit) information to the other unit. This can refer to a direct or indirect connection that is inherently wired and / or wireless. Furthermore, the two units can communicate with each other even if the transmitted information may be modified, processed, relayed, and / or routed between the first and second units. For example, the first unit can communicate with the second unit even if it passively receives information and does not actively send information to the second unit. As another example, the first unit can communicate with the second unit if at least one intermediate unit (e.g., a third unit located between the first and second units) processes information received from the first unit and sends the processed information to the second unit. In some non-limiting embodiments, a message can refer to a network packet (e.g., a data packet, etc.) that includes data.

[0040] As used herein, the terms “issuer,” “issuer institution,” “issuer bank,” or “payment device issuer” can refer to one or more entities that provide accounts for payment transactions, such as credit card payments and / or debit card payments, to individuals (e.g., users, customers, etc.). For example, an issuer institution may provide a customer with an account identifier, such as a primary account number (PAN), that uniquely identifies one or more accounts associated with said customer. In some non-limiting embodiments, an issuer may be associated with a bank identification number (BIN) that uniquely identifies the issuer institution. As used herein, “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 may include one or more authorization servers for authorizing transactions.

[0041] 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, the issuer may provide the user with an account identifier (e.g., a PAN, a token, etc.) that uniquely identifies one or more accounts associated with the user. The account identifier may be embodied in a payment device (e.g., a physical instrument used for making payment transactions, such as a payment card, credit card, debit card, gift card, etc.) and / or may be electronic information transmitted to the user, which the user can use for electronic payment transactions. In some non-limiting embodiments, the account identifier may be an original account identifier, wherein the original account identifier is provided to the user when an account associated with the account identifier is created. In some non-limiting embodiments, the account identifier may be a supplementary account identifier, which may include an account identifier provided to the user after the original account identifier has been provided to the user. For example, a supplementary account identifier may be provided to the user if the original account identifier has been forgotten, stolen, etc. In some non-limiting embodiments, the account identifier may be directly or indirectly associated with an issuing authority, such that the account identifier may be a token mapped to a PAN or other type of account identifier. The account identifier may be any combination of alphanumeric, character, and / or symbol, etc.

[0042] As used herein, the term "token" can refer to an account identifier used as a substitute or replacement for 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 for payment transactions without directly using the original account identifier. In some non-limiting embodiments, an original account identifier such as a PAN can be associated with multiple tokens for different individuals or purposes. In some non-limiting embodiments, a token can be associated with a PAN or other account identifiers in one or more data structures such that the token can be used for transactions without directly using an account identifier such as a PAN. In some examples, an account identifier such as a PAN can be associated with multiple tokens for different uses or purposes.

[0043] As used herein, the term "merchant" can refer to one or more entities (e.g., operators of retail businesses) that provide goods, services, and / or access to goods and / or services to users (e.g., customers, clients, etc.) based on transactions such as payment transactions. As used herein, the term "merchant system" can refer to one or more computer systems operated by or on behalf of a merchant, such as servers executing one or more software applications. As used herein, the term "product" can refer to one or more goods and / or services offered by a merchant.

[0044] As used herein, the term "point-of-sale (POS) device" can refer to one or more electronic devices that a merchant can use to conduct transactions (e.g., payment transactions) and / or process transactions. Alternatively or additionally, a POS device may include peripheral devices, card readers, scanning devices (e.g., barcode scanners, etc.). Communication receivers, near field communication (NFC) receivers, radio frequency identification (RFID) receivers and / or other contactless transceivers or receivers, contact-based receivers, payment terminals, etc.

[0045] 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 may include one or more POS devices, and / or other similar devices that can be used to conduct payment transactions. In some non-limiting embodiments, a POS system (e.g., a merchant POS system) may include one or more server computers programmed or configured to process online payment transactions via web pages, mobile applications, etc.

[0046] 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 an agreement between the transaction service provider and the issuing institution. In some non-limiting embodiments, the transaction service provider may include credit card companies, debit card companies, etc. Payment networks, or any other entity that processes transactions. As used herein, the term "transaction service provider system" can refer to one or more computer systems operated by or on behalf of a transaction service provider, such as a transaction service provider system executing one or more software applications. A transaction service provider system may include one or more processors, and in some non-limiting embodiments, may be operated by or on behalf of a transaction service provider.

[0047] As used herein, the term "payment device" can refer to payment cards (e.g., credit or debit cards), gift cards, smart cards (e.g., chip cards, integrated circuit cards, etc.), smart media, payroll cards, healthcare cards, wristbands, machine-readable media containing account information, keychain devices or pendants, RFID transponders, retailer discount or membership cards, etc. Payment devices may include volatile or non-volatile memory to store information (e.g., account identifiers, account holder's name, etc.).

[0048] 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, "client device" can refer to one or more devices that facilitate payment transactions, such as one or more POS devices used by a merchant. In some non-limiting embodiments, a client device can include computing devices configured to communicate with one or more networks and / or facilitate payment transactions, such as, but not limited to, one or more desktop computers, one or more mobile devices, and / or other similar devices. Furthermore, "client" can also refer to an entity that owns, utilizes, and / or operates a client device to facilitate payment transactions with a transaction service provider, such as a merchant.

[0049] 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 on a network such as the Internet or a private network, and in some examples, facilitate communication between other servers and / or client devices.

[0050] As used herein, the term "system" may 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. Furthermore, as used herein, references to "server" or "processor" may refer to the server and / or processor previously stated to perform the preceding steps or functions, different servers and / or processors, and / or combinations of servers and / or processors. For example, as used in the specification and claims, a first server and / or first processor stated to perform a first step or function may refer to the same or different servers and / or processors stated to perform a second step or function.

[0051] In some non-limiting embodiments, systems, computer-implemented methods, and computer program products are disclosed. For example, a system may include at least one processor programmed or configured to receive a data file, such as an XML data file, associated with a machine learning model. The data file may include data associated with one or more input parameters of the machine learning model. The at least one processor may be programmed or configured to generate a code generation template based on data included in the data file associated with one or more input parameters of the machine learning model. The code generation template may include one or more keys associated with one or more parameters of a transaction aggregation of a user's account, and the one or more parameters of the transaction aggregation of the user's account may be based on one or more parameters of multiple payment transactions involving the user's account. The at least one processor may be programmed or configured to generate an executable code file based on the code generation template. The executable code file may include instructions that, when executed by the at least one processor, cause the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account.

[0052] In this way, non-limiting embodiments of this disclosure can allow for the determination of aggregated data, for example, upon receiving a request associated with aggregated data, it can be determined that the aggregated data is low in resource intensity and does not require a large amount of computation time. Furthermore, non-limiting embodiments of this disclosure can allow for the creation of machine learning models for specific aggregated datasets without requiring recalculation of the aggregated data during each use instance of the machine learning model.

[0053] Now for reference Figure 1 The Figure 1 This is a diagram of an example environment 100 in which the apparatus, systems, methods, and / or products described herein can be implemented. Figure 1 As shown, environment 100 includes a code generator system 102, a user device 104, an orchestration system 106, an artificial intelligence (AI) risk assessment system 108, a short-term database 110, a long-term database 112, and a communication network 114. The code generator system 102, user device 104, orchestration system 106, AI risk assessment system 108, short-term database 110, and long-term database 112 can be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections (e.g., establishing connections for communication, etc.).

[0054] The code generator system 102 may include one or more devices capable of communicating with user device 104, orchestration system 106, artificial intelligence (AI) risk assessment system 108, short-term database 110, and long-term database 112 via communication network 114. For example, the code generator system 102 may include one or more computing devices, such as one or more servers and / or other similar devices. In some non-limiting embodiments, the code generator system 102 may be associated with a transaction service provider, as described herein. For example, the code generator system 102 may be operated by a transaction service provider and / or the code generator system 102 may be a component of a transaction service provider system.

[0055] User device 104 may include one or more devices capable of communicating via communication network 114 with code generator system 102, orchestration system 106, AI risk assessment system 108, short-term database 110, and long-term database 112. For example, user device 104 may include one or more computing devices, such as one or more servers, one or more client devices, one or more mobile devices, and / or other similar devices. In some non-limiting embodiments, user device 104 may be associated with a transaction service provider, as described herein. For example, user device 104 may be operated by a transaction service provider, and / or user device 104 may be a component of a transaction service provider system.

[0056] The orchestration system 106 may include one or more devices capable of communicating via the communication network 114 with the code generator system 102, user device 104, AI risk assessment system 108, short-term database 110, and long-term database 112. For example, the orchestration system 106 may include one or more computing devices, such as one or more servers and / or other similar devices. In some non-limiting embodiments, the orchestration system 106 may be associated with a transaction service provider, as described herein. For example, the orchestration system 106 may be operated by a transaction service provider, and / or the orchestration system 106 may be a component of a transaction service provider system.

[0057] AI risk assessment system 108 may include one or more devices capable of communicating via communication network 114 with code generator system 102, user device 104, orchestration system 106, short-term database 110, and long-term database 112. For example, AI risk assessment system 108 may include one or more computing devices, such as one or more servers and / or other similar devices. In some non-limiting embodiments, AI risk assessment system 108 may be associated with a transaction service provider, as described herein. For example, AI risk assessment system 108 may be operated by a transaction service provider, and / or AI risk assessment system 108 may be a component of a transaction service provider system.

[0058] Short-lived database 110 may include one or more devices capable of storing data in a data structure and communicating via communication network 114 with code generator system 102, user device 104, orchestration system 106, AI risk assessment system 108, and long-lived database 112. For example, short-lived database 110 may include one or more computing devices, such as one or more servers and / or other similar devices. In some non-limiting embodiments, short-lived database 110 may be a component of a system. For example, short-lived database 110 may be a component of code generator system 102 and / or orchestration system 106. In some non-limiting embodiments, short-lived database 110 may receive and / or store data associated with real-time (e.g., instant) payment transactions. For example, short-lived database 110 may receive data associated with real-time payment transactions from a messaging system such as Apache Kafka or IBM MQ, and short-lived database 110 may store data associated with real-time payment transactions in a data structure based on data received from the messaging system.

[0059] Long-term database 112 may include one or more devices capable of storing data in a data structure and communicating via communication network 114 with code generator system 102, user device 104, orchestration system 106, AI risk assessment system 108, and short-term database 110. For example, long-term database 112 may include one or more computing devices, such as one or more servers and / or other similar devices. In some non-limiting embodiments, long-term database 112 may be a component of a system. For example, long-term database 112 may be a component of code generator system 102 and / or orchestration system 106. In some non-limiting embodiments, long-term database 112 may receive and / or store data associated with a user profile based on transaction data associated with payment transactions made by a user associated with a user profile. For example, long-term database 112 may receive data associated with a user profile from a file system such as an Apache Hadoop system, and long-term database 112 may store data associated with a user profile based on data received from the file system.

[0060] The communication network 114 may include one or more wired and / or wireless networks. For example, the communication network 114 may include cellular networks (e.g., Long Term Evolution (LTE) networks, third-generation (3G) networks, fourth-generation (4G) networks, fifth-generation (5G) networks, Code Division Multiple Access (CDMA) networks, etc.), Public Land Mobile Networks (PLMN), Local Area Networks (LAN), Wide Area Networks (WAN), Metropolitan Area Networks (MAN), Telephone Networks (e.g., Public Switched Telephone Network (PSTN)), Private Networks, Self-organizing Networks, Intranets, the Internet, Fiber-based Networks, Cloud Computing Networks, etc., and / or some or a combination of all or other types of networks.

[0061] Provided as an example Figure 1 The number and arrangement of systems and / or devices are shown. Additional systems and / or devices, fewer systems and / or devices, different systems and / or devices, or devices may exist in conjunction with... Figure 1 The systems and / or devices shown are arranged in different ways. Furthermore, they can be implemented within a single system and / or a single device. Figure 1 The two or more systems and / or devices shown, or Figure 1 The single system or device shown may be implemented as multiple distributed systems or devices. Alternatively, a group of systems or devices in environment 100 (e.g., one or more systems, one or more devices) may perform one or more functions described as being performed by another group of systems or devices in environment 100.

[0062] Now for reference Figure 2 The Figure 2 This is a diagram of example components of device 200. Device 200 may correspond to code generator system 102 (e.g., one or more devices of code generator system 102), user device 104, orchestration system 106 (e.g., one or more devices of orchestration system 106), AI risk determination system 108 (e.g., one or more devices of AI risk determination system 108), short-term database 110, and / or long-term database 112. In some non-limiting aspects or embodiments, code generator system 102, user device 104, orchestration system 106, AI risk determination system 108, short-term database 110, and / or long-term database 112 may include at least one device 200 and / or at least one component of device 200. Figure 2 As shown, device 200 may include bus 202, processor 204, memory 206, storage component 208, input component 210, output component 212 and communication interface 214.

[0063] Bus 202 may include components that enable communication between components of device 200. In some non-limiting aspects or embodiments, processor 204 may be implemented in hardware, software, or a combination of hardware and software. For example, processor 204 may include a processor (e.g., a central processing unit (CPU), graphics processing unit (GPU), accelerated processing unit (APU), etc.), microprocessor, digital signal processor (DSP), and / or any processing component that can be programmed to perform functions (e.g., a field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), etc.). Memory 206 may include random access memory (RAM), read-only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic memory, optical memory, etc.) that stores information and / or instructions for use by processor 204.

[0064] Storage component 208 may store information and / or software associated with the operation and use of device 200. For example, storage component 208 may include hard disk (e.g., magnetic disk, optical disk, magneto-optical disk, solid-state disk, etc.), compressed optical disk (CD), digital versatile optical disk (DVD), floppy disk, cassette tape, magnetic tape and / or another type of computer-readable medium, and corresponding drives.

[0065] Input component 210 may include components that allow device 200 to receive information, such as via user input (e.g., touchscreen display, keyboard, keypad, mouse, button, switch, microphone, camera, etc.). Alternatively, input component 210 may include sensors for sensing information (e.g., Global Positioning System (GPS) component, accelerometer, gyroscope, actuator, etc.). Output component 212 may include components that provide output information from device 200 (e.g., display, speaker, one or more light-emitting diodes (LEDs), etc.).

[0066] Communication interface 214 may include transceiver components (e.g., transceiver, separate receiver and transmitter, etc.) that enable device 200 to communicate with other devices, for example, via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 214 may allow device 200 to receive information from another device and / or provide information to another device. For example, communication interface 214 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, etc. Interfaces, cellular network interfaces, etc.

[0067] Apparatus 200 can perform one or more of the processes described herein. Apparatus 200 can perform these processes based on software instructions stored in a computer-readable medium, such as memory 206 and / or storage component 208, executed by processor 204. Computer-readable medium (e.g., non-transient computer-readable medium) is defined herein as a non-transient memory device. A non-transient memory device includes memory space located within a single physical storage device or memory space distributed across multiple physical storage devices.

[0068] Software instructions may be read from another computer-readable medium or from another device into memory 206 and / or storage component 208 via communication interface 214. When executed, the software instructions stored in memory 206 and / or storage component 208 may cause processor 204 to perform one or more processes described herein. Alternatively or additionally, hard-wired circuitry may be used in place of or in combination with the software instructions to perform one or more processes described herein. Therefore, the embodiments or aspects described herein are not limited to any particular combination of hardware circuitry and software.

[0069] The memory 206 and / or storage component 208 may include a data storage device or one or more data structures (e.g., a database). The device 200 may be able to retrieve information from the data storage device or one or more data structures in the memory 206 and / or storage component 208, store information in the data storage device or one or more data structures, or search for information stored in the data storage device or one or more data structures. For example, the information may include encrypted data, input data, output data, transaction data, account data, or any combination thereof.

[0070] Provided as an example Figure 2 The number and arrangement of components are shown. In some non-limiting aspects or embodiments, device 200 may include components related to... Figure 2 The components shown are those that are additional, fewer, different, or arranged differently compared to other components. Alternatively, a set of components of device 200 (e.g., one or more components) may perform one or more functions described as being performed by another set of components of device 200.

[0071] Now for reference Figure 3 The Figure 3This is a flowchart of a non-limiting embodiment of a process 300 for generating code to retrieve aggregated data for a machine learning model. In some non-limiting aspects or embodiments, one or more functions described with respect to process 300 may be performed by code generator system 102 (e.g., entirely, partially, etc.). In some non-limiting embodiments, one or more steps of process 300 may be performed by another device or group of devices different from and / or including code generator system 102, such as user device 104, orchestration system 106, and / or AI risk assessment system 108 (e.g., entirely, partially, etc.).

[0072] like Figure 3 As shown, at step 302, process 300 may include receiving a data file associated with a machine learning model. For example, code generator system 102 may receive a data file including one or more input parameters of a machine learning model. In some non-limiting embodiments, the one or more input parameters of the machine learning model may include one or more features associated with the machine learning model. For example, the one or more input parameters of the machine learning model may correspond to one or more features used for training and / or validating the machine learning model.

[0073] In some non-limiting embodiments, one or more input parameters of the machine learning model may include one or more keys associated with one or more parameters of a transaction aggregation of the user's account. The one or more keys associated with one or more parameters of the transaction aggregation of the user's account may correspond to one or more features used to train and / or validate the machine learning model. In some non-limiting embodiments, the machine learning model may include a risk determination machine model. For example, the machine learning model may include a risk determination machine model used by the AI ​​risk determination system 108 to determine the risk associated with the authorization of payment transactions (e.g., real-time payment transactions) made using the user's account.

[0074] In some non-limiting embodiments, one or more parameters of a user's account transaction aggregation may be based on one or more parameters of multiple payment transactions involving the user's account. For example, one or more parameters of the transaction aggregation may include multiple payment transactions made using the user's account during a time interval, the total transaction amount of the multiple payment transactions made using the user's account during the time interval, multiple IP addresses involved in the multiple payment transactions made using the user's account during the time interval (e.g., multiple IP addresses each associated with different computing devices), a list of IP addresses associated with the multiple payment transactions made using the user's account during the time interval (e.g., a list of IP addresses each associated with different computing devices involved), etc.

[0075] In some non-limiting embodiments, the code generator system 102 may store one or more parameters of a user's account transaction aggregate. For example, the code generator system 102 may store one or more parameters of a user's account transaction aggregate as a user profile of the user's account in a long-term database 112. One or more parameters of the user's account transaction aggregate (e.g., the user profile of the user's account) may be assigned to the user's account identifier in the long-term database 112.

[0076] In some non-limiting embodiments, the code generator system 102 may receive a data file from the user device 104 via a web application. For example, the code generator system 102 may receive a data file from the user device 104 via a web application configured on the user device 104. Data included in the data file (e.g., data associated with one or more input parameters of a machine learning model) may be based on data received via the web application. In some non-limiting embodiments, the data file may include an Extensible Markup Language (XML) data file. For example, the data file may include data in an XML data file format.

[0077] like Figure 3 As shown, at step 304, process 300 may include generating a code generation template based on a data file. For example, code generator system 102 may generate a code generation template based on a data file received from user device 104. In some non-limiting embodiments, the code generation template may include a template having fields with one or more input parameters based on a machine learning model (e.g., a risk determination machine learning model). In some non-limiting embodiments, code generator system 102 may generate a code generation template based on a machine learning model. For example, code generator system 102 may generate a code generation template based on an identifier of a machine learning model, such as an identifier of a risk determination machine learning model. In some non-limiting embodiments, the identifier of the machine learning model may be included in the data file received from user device 104.

[0078] In some non-limiting embodiments, the code generator system 102 may generate a code generation template as a template for SQL queries. For example, the code generator system 102 may generate a code generation template as a template for SQL queries based on data included in a data file received from the user device 104. In some non-limiting embodiments, the template for SQL queries may include one or more keys associated with one or more parameters of a transaction aggregation of the user's account.

[0079] like Figure 3As shown, at step 306, process 300 may include generating an executable code file based on a code generation template. For example, code generator 102 may generate an executable code file based on a code generation template. The executable code file may include instructions that, when executed, cause transaction aggregation data associated with a transaction aggregation of a user's account to be retrieved. In some non-limiting embodiments, the transaction aggregation data associated with a transaction aggregation of a user's account may include one of a plurality of values ​​of one or more parameters of the user's account's transaction aggregation. For example, the transaction aggregation data associated with a transaction aggregation of a user's account may include multiple payment transactions made using the user's account during a time interval, wherein the number of the multiple payment transactions is equal to 7. In another example, the transaction aggregation data associated with a transaction aggregation of a user's account may include the total transaction amount of multiple payment transactions made using the user's account during a time interval, wherein the total transaction amount of the multiple payment transactions is equal to $534.56. In another example, the transaction aggregation data associated with a transaction aggregation of a user's account may include multiple IP addresses involved in multiple payment transactions made using the user's account during a time interval, and the number of IP addresses is equal to 6.

[0080] In some non-limiting embodiments, the code generator system 102 may store transaction aggregation data associated with a user's account (e.g., one of multiple values ​​of one or more parameters of the user's account's transaction aggregation). For example, the code generator system 102 may store one or more values ​​of one or more parameters of the user's account's transaction aggregation in the user's account's user profile in the long-term database 112. One or more values ​​of one or more parameters of the user's account's transaction aggregation (e.g., the user's account's user profile) may be assigned to the user's account's account identifier in the long-term database 112.

[0081] In some non-limiting embodiments, the executable code file may include instructions that, when executed, cause long-term transaction aggregation data associated with transaction aggregations of a user's account to be retrieved from the long-term database 112. Alternatively, the executable code file may include instructions that, when executed, cause short-term transaction aggregation data associated with transaction aggregations of a user's account to be retrieved from the short-term database 110.

[0082] In some non-limiting embodiments, the code generator system 102 may execute executable code files and retrieve transaction aggregation data associated with transaction aggregations of a user's account from the short-term database 110 and / or the long-term database 112. Alternatively, the orchestration system 106 and / or the AI ​​risk determination system 108 may execute executable code files and retrieve transaction aggregation data associated with transaction aggregations of a user's account from the short-term database 110 and / or the long-term database 112.

[0083] In some non-limiting embodiments, the code generator system 102 may generate an executable code file to include instructions that, when executed, cause the retrieval of transaction aggregation data associated with transaction aggregation data of a user's account from predetermined databases of multiple databases. For example, the code generator system 102 may generate an executable code file to include instructions that, when executed, cause the retrieval of transaction aggregation data associated with transaction aggregation of a user's account from predetermined databases of short-term database 110 and long-term database 112. In some non-limiting embodiments, the code generator system 102 may determine predetermined databases among multiple databases based on data included in a data file received from user device 104. For example, the code generator system 102 may determine predetermined databases among multiple databases based on one or more input parameters of a machine learning model and / or one or more keys associated with one or more parameters of transaction aggregation of a user's account. Alternatively or additionally, the code generator system 102 may determine predetermined databases among multiple databases based on an identifier of a machine learning model included in a data file.

[0084] In some non-limiting embodiments, orchestration system 106 may receive a request for a risk assessment determination of payment transactions involving a user's account. For example, orchestration system 106 may receive such a request from user device 104. In some non-limiting embodiments, the request for a risk assessment determination may include an account identifier of the user's account. In some non-limiting embodiments, orchestration system 106 may send a risk assessment determination request based on receiving it from user device 104. For example, orchestration system 106 may send a risk assessment determination request to code generator system 102 based on receiving such a request.

[0085] In some non-limiting embodiments, the code generator system 102, orchestration system 106, and / or AI risk determination system 108 can retrieve transaction aggregation data associated with transaction aggregations of a user's account from the short-term database 110 and / or the long-term database 112. For example, the orchestration system 106 can retrieve transaction aggregation data associated with transaction aggregations from the short-term database 110 and / or the long-term database 112 based on the account identifier of the user's account included in the request for risk assessment determination. In this example, the code generator system 102, orchestration system 106, and / or AI risk determination system 108 can determine a user profile corresponding to the account identifier of the user's account and can retrieve transaction aggregation data associated with transaction aggregations of the user's account from the user profile. In some non-limiting embodiments, the code generator system 102, orchestration system 106, and / or AI risk determination system 108 can retrieve short-term aggregation data associated with transaction aggregations of a user's account from the short-term database and / or retrieve long-term aggregation data associated with transaction aggregations of a user's account from the long-term database 112.

[0086] In some non-limiting embodiments, the code generator system 102, orchestration system 106, and / or AI risk assessment system 108 can retrieve transaction aggregation data associated with transaction aggregations of a user's account from the short-term database 110 and / or the long-term database 112 based on executing executable code files. For example, the code generator system 102, orchestration system 106, and / or AI risk assessment system 108 can retrieve transaction aggregation data associated with transaction aggregations of a user's account based on executing executable code files within predetermined time intervals. In some non-limiting embodiments, the predetermined time interval may include daily time intervals, weekly time intervals, monthly time intervals, etc.

[0087] In some non-limiting embodiments, the AI ​​risk assessment system 108 may use transaction aggregation data associated with transaction aggregations of a user's account to determine a risk assessment score associated with payment transactions involving the user's account. For example, the AI ​​risk assessment system 108 may use transaction aggregation data associated with transaction aggregations of a user's account as input to a risk assessment machine learning model to determine the risk assessment score. In some non-limiting embodiments, the AI ​​risk assessment system 108 may send the determined risk assessment score to the orchestration system 106. In some non-limiting embodiments, the orchestration system 106 may determine whether the risk assessment score associated with the payment transactions involving the user's account meets a risk assessment threshold. In some non-limiting embodiments, the orchestration system 106 may perform an operation based on the determination that the risk assessment score associated with the payment transactions involving the user's account meets the risk assessment threshold. In some non-limiting embodiments, the orchestration system 106 may abandon the operation or perform a different operation based on the determination that the risk assessment score associated with the payment transactions involving the user's account does not meet the risk assessment threshold. In some non-limiting embodiments, orchestration system 106 may send a message indicating that a payment transaction has been authorized based on determining that the risk assessment score associated with a payment transaction involving a user's account meets a risk assessment threshold. Orchestration system 106 may also send a message indicating that a payment transaction has not been authorized based on determining that the risk assessment score associated with a payment transaction involving a user's account does not meet a risk assessment threshold.

[0088] Now for reference Figures 4A-4E This illustrates a non-limiting embodiment of an implementation 400 for generating code to retrieve aggregated data for a machine learning model. Figure 4A As indicated by reference numeral 415 in the accompanying drawings, the orchestration system 106 can receive an XML data file associated with a machine learning model. In some non-limiting embodiments, the XML data file includes data associated with one or more input parameters of the machine learning model. Figure 4A As shown by reference numeral 420 in the accompanying drawings, the code generator system 102 can send an XML data file to the code generator system 102 based on the orchestration system 106 and receive an XML data file from the orchestration system 106.

[0089] like Figure 4BAs shown by reference numeral 425 in the accompanying drawings, the code generator system 102 can generate a code generation template based on data associated with one or more input parameters of a machine learning model, included in an XML data file. In some non-limiting embodiments, the code generation template includes one or more keys associated with one or more parameters of a transaction aggregation of a user's account, and the one or more parameters of the transaction aggregation of the user's account may be based on one or more parameters of multiple payment transactions involving the user's account. Figure 4B As indicated by reference numeral 430 in the accompanying drawings, the code generator system 102 can generate executable code files based on a code generation template. In some non-limiting embodiments, the executable code file includes instructions that, when executed by at least one processor, cause at least one processor to retrieve transaction aggregation data associated with a transaction aggregation of a user's account.

[0090] like Figure 4C As indicated by reference numeral 435 in the accompanying drawings, the orchestration system 106 can receive from the user device 104 a request for a risk assessment determination of payment transactions (e.g., real-time payment transactions) involving the user's account. Figure 4D As shown by reference numeral 440 in the attached figure, the orchestration system 106 can retrieve transaction aggregation data associated with the transaction aggregation of a user's account.

[0091] like Figure 4E As shown by reference numeral 445 in the attached diagram, the orchestration system 106 can send transaction aggregation data associated with the transaction aggregation of a user's account to the AI ​​risk determination system 108. For example... Figure 4E As shown by reference numeral 450 in the attached figure, the AI ​​risk assessment system 108 can determine a risk assessment score associated with payment transactions involving a user's account based on transaction aggregation data associated with the transaction aggregation. For example, the AI ​​risk assessment system 108 can use transaction aggregation data associated with a user's account as input to a machine learning model to determine the risk assessment score associated with payment transactions involving the user's account. Figure 4E As indicated by reference numeral 455 in the attached diagram, the orchestration system 106 can receive risk assessment scores associated with payment transactions involving user accounts from the AI ​​risk determination system 108. Figure 4E As shown by reference numeral 460 in the attached figure, the orchestration system 106 can perform operations based on risk assessment scores.

[0092] 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 system for generating code to retrieve aggregated data for a machine learning model, comprising: At least one processor, which is programmed or configured to: Receive an XML data file, wherein the XML data file includes data associated with one or more input parameters of a machine learning model; Based on the data generated in the XML data file, a code generation template associated with one or more input parameters of the machine learning model is generated. The code generation template includes a template having fields based on the one or more input parameters of the machine learning model. The code generation template includes one or more keys associated with one or more parameters of a user's account transaction aggregation. The one or more keys associated with the one or more parameters of the user's account transaction aggregation correspond to one or more features used for training and validating the machine learning model. The one or more parameters of the user's account transaction aggregation are based on one or more parameters involving multiple payment transactions of the user's account. An executable code file is generated based on the code generation template, wherein the executable code file includes instructions that, when executed by at least one processor, cause at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account.

2. The system of claim 1, wherein the code generation template includes a template for an SQL query, and wherein the template for the SQL query includes the one or more keys associated with one or more parameters of the transaction aggregation of the user's account.

3. The system according to claim 1, wherein, When the executable code file is generated, the at least one processor is programmed or configured to: The executable code file is generated, which, when executed by at least one processor, causes the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database among a plurality of databases.

4. The system of claim 1, wherein the at least one processor is further programmed or configured to: Receive a request from the client device to determine the risk assessment of payment transactions involving the user's account; Retrieve first transaction aggregation data associated with the first transaction aggregation of the user's account; and Using the first transaction aggregate data associated with the first transaction aggregate of the user's account as input to the machine learning model, a risk assessment score associated with the payment transaction involving the user's account is determined.

5. The system according to claim 4, wherein, When retrieving first transaction aggregation data associated with the first transaction aggregation of the user's account, the at least one processor is programmed or configured to: Retrieve short-term aggregate data associated with the first transaction aggregate of the user's account from the short-term database; and Retrieve long-term aggregate data associated with the first transaction aggregate of the user's account from the long-term database.

6. The system according to claim 4, wherein, When retrieving first transaction aggregate data associated with a first transaction aggregate of the user's account, the at least one processor is programmed or configured to: Based on executing the executable code file, the first transaction aggregate data associated with the first transaction aggregate of the user's account is retrieved from one or more databases.

7. The system according to claim 1, wherein, When the XML data file is received, the at least one processor is programmed or configured to: The XML data file is received from a client device via a web application, and the data associated with one or more input parameters of the machine learning model is based on the data received via the web application.

8. A computer-implemented method for generating code to retrieve aggregated data for a machine learning model, comprising: At least one processor is used to receive a data file, wherein the data file includes data associated with one or more input parameters of a machine learning model; At least one processor generates a code generation template based on the data included in the data file that is associated with one or more input parameters of the machine learning model, wherein the code generation template includes a template having fields based on the one or more input parameters of the machine learning model, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of a user's account, wherein the one or more keys associated with the one or more parameters of the transaction aggregate of the user's account correspond to one or more features used for training and validating the machine learning model; as well as An executable code file is generated using at least one processor based on the code generation template, wherein the executable code file includes instructions that, when executed by the at least one processor, cause the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account.

9. The method of claim 8, wherein the file used to generate the executable code file comprises: The executable code file is generated, which, when executed by at least one processor, causes the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database among a plurality of databases.

10. The method of claim 8, further comprising: Receive a request from the client device to determine the risk assessment of payment transactions involving the user's account; Retrieve first transaction aggregation data associated with the first transaction aggregation of the user's account; as well as Using the first transaction aggregate data associated with the first transaction aggregate of the user's account as input to the machine learning model, a risk assessment score associated with the payment transaction involving the user's account is determined.

11. The method of claim 10, wherein retrieving first transaction aggregation data associated with the first transaction aggregation of the user's account comprises: Retrieve short-term aggregate data associated with the first transaction aggregate of the user's account from the short-term database; as well as Retrieve long-term aggregate data associated with the first transaction aggregate of the user's account from the long-term database.

12. The method of claim 10, wherein retrieving first transaction aggregation data associated with the first transaction aggregation of the user's account, the at least one processor is programmed or configured to: Based on executing the executable code file, the first transaction aggregate data associated with the first transaction aggregate of the user's account is retrieved from one or more databases.

13. The method of claim 10, further comprising: Determine whether the risk assessment score associated with the payment transaction involving the user's account meets the risk assessment threshold; as well as The operation is performed based on the risk assessment score associated with the payment transaction involving the user's account, which is determined to meet a risk assessment threshold.

14. The method of claim 8, wherein receiving the data file comprises: An XML data file is received from a client device via a web application, and the data associated with one or more input parameters of the machine learning model is based on the data received via the web application.

15. A computer program product for generating code to retrieve aggregated data of a machine learning model, comprising at least one non-transient computer-readable medium, said at least one non-transient computer-readable medium comprising one or more instructions, said one or more instructions causing said at least one processor, when executed by said at least one processor: Receive XML data files associated with machine learning models; A code generation template is generated based on the data file associated with the machine learning model, wherein the code generation template includes a template having fields based on the one or more input parameters of the machine learning model, wherein the code generation template includes one or more keys associated with one or more parameters of a transaction aggregate of the user's account, wherein the one or more keys associated with the one or more parameters of the transaction aggregate of the user's account correspond to one or more features used for training and validating the machine learning model, wherein the one or more parameters of the transaction aggregate of the user's account are based on one or more parameters of multiple payment transactions involving the user's account; and An executable code file is generated based on the code generation template, wherein the executable code file includes instructions that, when executed by the at least one processor, cause the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account.

16. The computer program product of claim 15, wherein the code generation template includes a template for an SQL query, and wherein the template for the SQL query includes the one or more keys associated with one or more parameters of the transaction aggregation of the user's account.

17. The computer program product according to claim 16, wherein, The one or more instructions that cause the at least one processor to generate the executable code file cause the at least one processor to: The executable code file is generated, which, when executed by at least one processor, causes the at least one processor to retrieve transaction aggregation data associated with the transaction aggregation of the user's account from a predetermined database among a plurality of databases.

18. The computer program product of claim 17, wherein the one or more instructions further cause the at least one processor to: Receive a request from the client device to determine the risk assessment of payment transactions involving the user's account; Retrieve first transaction aggregation data associated with the first transaction aggregation of the user's account; and Using the first transaction aggregate data associated with the first transaction aggregate of the user's account as input to the machine learning model, a risk assessment score associated with the payment transaction involving the user's account is determined.

19. The computer program product according to claim 17, wherein, The one or more instructions that cause the at least one processor to retrieve the first transaction aggregate data associated with the first transaction aggregate of the user's account cause the at least one processor to: Retrieve short-term aggregate data associated with the first transaction aggregate of the user's account from the short-term database; and Retrieve long-term aggregate data associated with the first transaction aggregate of the user's account from the long-term database.

20. The computer program product according to claim 15, wherein, The at least one processor receives one or more instructions from the XML data file, causing the at least one processor to: The XML data file is received from a client device via a web application, and the data associated with one or more input parameters of the machine learning model is based on the data received via the web application.

Images