Risk control method, device and system based on shop asset evaluation and storage medium

Abstract

The invention relates to a risk control method based on store asset evaluation, and the method comprises the steps: obtaining store data of a target user from an e-commerce platform through an API interface, processing the store data into derivative indexes, and obtaining an asset evaluation value of the target user through a store asset value evaluation model (preset algorithm) which can be employed by a financial institution, and finally, generating a loan stroke control management strategy of the target user (cross-border e-commerce seller / enterprise) through the proportion between the asset evaluation value and the loan amount of the target user, so as to solve the problem that the risk in loan of the cross-border e-commerce enterprise is difficult to monitor due to the fact that the asset evaluation of the cross-border e-commerce enterprise is difficult.

Description

Technical Field

[0001] The present application relates to the field of cross-border e-commerce risk control technology, and in particular to a risk control method, device, system and storage medium based on store asset evaluation. Background Art

[0002] With the continuous development of cross-border e-commerce, the demand for capital by these businesses is growing. Small and medium-sized enterprises (SMEs) in this sector present unique operational models and capital flows. They have limited liquidity, slow cash flow, and are susceptible to exchange rate fluctuations and losses in currency transactions. The export tax rebate process is time-consuming, and the operating models of e-commerce platforms can lead to capital tie-up. Furthermore, financial institutions lack access to the actual operating data of cross-border e-commerce companies on overseas platforms, while cross-border e-commerce platforms cannot directly transmit raw data domestically due to privacy protection policies in various countries.

[0003] Given the above situation, financial institutions often find themselves in a state of uncertainty when dealing with cross-border e-commerce companies. They find it difficult to accurately assess and predict their future earnings and repayment capacity. Furthermore, monitoring risk management during lending becomes extremely difficult. Summary of the Invention

[0004] This application provides a risk control method, device, system and storage medium based on store asset assessment to solve the problem of difficulty in asset assessment of cross-border e-commerce enterprises in the existing technology, which makes it difficult to monitor the loan risks of cross-border e-commerce enterprises.

[0005] In a first aspect, this application provides a risk control method based on store asset evaluation, including:

[0006] Obtain target users’ store data from e-commerce platforms through API interfaces;

[0007] Calculating derivative indicators on the store data to generate evaluation data;

[0008] Obtaining an asset evaluation value based on the evaluation data and a preset algorithm;

[0009] If the asset evaluation value is less than the target user's loan amount, the target user will be identified as a risky loan user and a corresponding risk control management strategy will be generated.

[0010] Furthermore, the preset algorithm is:

[0011] Asset evaluation value = (S1+S2*a+S3*b+M1)*c+M2+M3, where:

[0012] S1 is the total inventory value of all products in the current evaluation store with an inventory age of 0-90 days. The current evaluation store is one or more stores under the name of the target user;

[0013] S2 is the total inventory value of all products in the current evaluated store with an inventory age of 91-180 days;

[0014] S3 is the total inventory value of all products in the current evaluation store with an inventory age of 181-270 days;

[0015] a and b are constants, a = 0.8, b = 0.5;

[0016] M1 is the sales amount awaiting payment, which means the sales amount for which orders have been shipped but payment has not yet been received;

[0017] c is the repayment rate for the past six natural months starting from the current time;

[0018] M2 is the amount in transit, which indicates the amount that has been paid by the e-commerce platform but has not yet entered the target user's receiving account;

[0019] M3 is the reserved amount, which represents the amount reserved in the target user's receiving account to pay for potential or existing transaction disputes.

[0020] Furthermore, the store data includes at least inventory reports, sales orders, and payment records, and the derivative indicator calculation includes:

[0021] Counting the inventory quantity of each product code from the inventory report, and then summarizing the inventory data of the total product code of the store;

[0022] Calculate all quantity-related indicators based on the time dimension, including at least the repayment amount for the past six natural months starting from the current time;

[0023] Summarize based on user dimensions, including at least: calculating the total collection amount of all stores authorized by the target user in the past 6 natural months starting from the current time and the inventory value of all inventory of the target user.

[0024] Furthermore, after obtaining the target user's store data from the e-commerce platform through the API interface, the method further includes:

[0025] Performing data cleaning on the store data to remove invalid data and abnormal data;

[0026] Convert the cleaned data into a data format that is easy to interpret and store.

[0027] Furthermore, if the asset evaluation value is less than the target user's loan amount, the target user is identified as a risky loan user, and a corresponding risk control management strategy is generated, including:

[0028] The target users are identified as different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels.

[0029] Furthermore, the target user is identified as having different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels, including:

[0030] If the ratio of the asset evaluation value to the loan amount is less than a first preset value, the target user is identified as a high-risk user and a heavy management policy is generated.

[0031] Furthermore, the target user is identified as having different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels, including:

[0032] If the ratio of the asset assessment value to the loan amount is less than a second preset value, the target user is identified as a medium-risk user and a moderate management strategy is generated, wherein the second preset value is greater than the first preset value, and the control strength of the moderate management strategy is weaker than that of the heavy management strategy.

[0033] In a second aspect, the present application provides a risk control device based on store asset assessment, comprising:

[0034] The data acquisition module is used to obtain the target user's store data from the e-commerce platform through the API interface;

[0035] A derivative indicator calculation module, used to calculate derivative indicators on the store data to generate evaluation data;

[0036] An asset evaluation module, configured to obtain an asset evaluation value based on the evaluation data and a preset algorithm;

[0037] The risk control module is used to identify the target user as a risky loan user if the asset evaluation value is less than the loan amount of the target user, and generate a corresponding risk control management strategy.

[0038] In a third aspect, the present application provides a risk control system based on store asset evaluation, including an API interface calling module, a main control module and a financial institution docking module, wherein:

[0039] The API interface calling module obtains store data of the e-commerce platform by connecting to the API data interface of the e-commerce platform;

[0040] The main control module performs any one of the technical processing steps provided in the first aspect above;

[0041] The financial institution docking module is used to send risk control management strategies to the target user's loan amount institution.

[0042] In a fourth aspect, the present application also provides a computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the risk control method based on store asset assessment described in the present application.

[0043] The method provided in the embodiment of the present application obtains the store data of the target user from the e-commerce platform through the API interface, processes the store data into derivative indicators, and then obtains the asset evaluation value of the target user through a store asset value evaluation model (preset algorithm) that can be adopted by financial institutions. Finally, through the ratio between the asset evaluation value and the target user's loan amount, a loan risk management strategy for the target user (cross-border e-commerce seller / enterprise) is generated to solve the problem of difficulty in asset evaluation of cross-border e-commerce enterprises, which leads to difficulty in monitoring the loan risks of cross-border e-commerce enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0047] Figure 1 A flow chart of a risk control method based on store asset assessment provided in an embodiment of the present application;

[0048] Figure 2 A module flow chart of a risk control device based on store asset assessment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] The disclosure below provides many different embodiments or examples for implementing different configurations of the present invention. To simplify the disclosure of the present invention, the components and configurations of specific examples are described below. Of course, these are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numerals and / or letters in different examples. Such repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or configurations discussed.

[0051] In the existing credit field, the credit assessment and credit limit calculation for borrowers need to be based on accurate, true, and generally recognized value assessment methods by financial institutions. In traditional credit business, real estate, factories, equipment, bonds, etc. are generally used as collateral for fair value assessment. However, in the cross-border e-commerce industry, since there are no generally recognized collateral such as fixed assets, they cannot be included in the assessment system of financial institutions. In response to this problem, this application provides a risk control method based on store asset evaluation. Based on the characteristics of the cross-border e-commerce industry, the e-commerce platform account, that is, the online store, is selected as the evaluation object. By comprehensively evaluating and calculating store assets such as store account funds and inventory goods, the store assets are calculated to solve the problem that the cross-border e-commerce industry cannot effectively evaluate corporate assets to determine credit limits when applying for loans from financial institutions, which makes it difficult to monitor the loan risks of cross-border e-commerce companies.

[0052] Figure 1 An embodiment of the present application provides a risk control method based on store asset assessment, the method comprising:

[0053] S101. Obtain store data of target users from the e-commerce platform through an API interface;

[0054] The risk control method based on store asset evaluation provided by this application can be used to develop a software system platform for evaluating the store assets of cross-border e-commerce sellers to assess their asset value, and then compare it with the loan amount of the cross-border e-commerce sellers to generate a corresponding risk control management strategy, which can be sent to the bank system connected to the system platform. Among them, the target user here refers to the cross-border e-commerce seller. In one embodiment, the e-commerce platform is the Amazon platform, and the software system platform corresponding to this application obtains data authorization from the Amazon platform by applying for the Amazon platform SP-API data interface. The target user authorizes the store through the Amazon platform, so that the system platform can obtain the target user's store data from the Amazon platform through the API interface. Specifically, the store data includes inventory reports, sales orders, collection records and other data that can reflect the value of the store's assets.

[0055] Furthermore, in order to ensure that the store data for evaluation is valid data and to improve the accuracy of subsequent evaluations, this application first cleans the store data to remove invalid data and abnormal data, and then converts the cleaned data into a data format that is easy to interpret and store, such as storing the data in a relational database. For example, when calculating the repayment amount indicator for the past six natural months, it is necessary to filter the data obtained through the function getEventGroups and filter the data with ProcessingStatus as 'Closed' and FundTransferStatus as 'Succeeded' for calculation. However, the data obtained through the API interface call may have an empty json format, so these abnormal data need to be cleaned. It should be noted that storing data in a relational database is a way to convert data into a data format that is easy to interpret and store, and it can also be other data storage methods. For example, the data obtained through the getEvents interface is in json format and needs to be stored on S3 first, then flattened into relational data through the lambda function, and then read and written through DynamoDB and stored in Redshift to complete the storage of json format data in the relational database.

[0056] S102: Calculate derivative indicators on the store data to generate evaluation data;

[0057] This application conducts an in-depth analysis of the operating methods of Amazon platform stores, samples and analyzes Amazon store-related data using the evaluation logic commonly used in the financial industry, and processes the store data into derivative indicators through logical script operations. Ultimately, it forms a store asset value evaluation model that can be adopted by financial institutions. This model is used to accurately evaluate the assets of sellers on the Amazon platform, allowing financial institutions to understand the sellers' future profitability and repayment ability. The store asset value evaluation model mentioned here that can be adopted by financial institutions can be understood as the preset algorithm in this application.

[0058] Simply put, a derived indicator is a metric calculated secondary to a formula. For example, inventory quantity is an atomic indicator, while the inventory quantity per product code is a derived indicator. Specifically, any addition, subtraction, multiplication, or division of an atomic indicator, as well as the addition of modifiers, can be considered a derived indicator. In other words, a derived indicator = atomic indicator + time period + modifier.

[0059] In the embodiment of the present application, the derivative index calculation includes the following:

[0060] 1. Count the inventory quantity of each product code from the inventory report, and then summarize the inventory data of the total product code of the store;

[0061] 2. Calculate all quantity-related indicators based on the time dimension, including at least the repayment amount for the past six natural months starting from the current time;

[0062] 3. Summarize based on user dimensions, including at least: calculating the total collection amount of all stores authorized by the target user in the past six natural months starting from the current time and the inventory value of all inventory of the target user.

[0063] For example, when calculating the indicator of the repayment amount in the past six natural months, the repayment records in the past six natural months are first counted, and the repayment amounts for each month are added together to obtain the repayment amount for the past six natural months.

[0064] It should be noted that this application processes and calculates derivative indicators for each indicator involved in the preset algorithm to obtain evaluation data, which is used to input the preset algorithm to estimate the asset value of the target user, that is, to obtain the asset evaluation value of the target user.

[0065] S103: Obtaining an asset evaluation value based on the evaluation data and a preset algorithm;

[0066] In the embodiment of the present application, a preset algorithm is used to obtain the asset evaluation value of the target user. Specifically, the preset algorithm is:

[0067] Asset evaluation value = (S1+S2*a+S3*b+M1)*c+M2+M3, where:

[0068] S1 is the total inventory value of all products in the current evaluation store with an inventory age of 0-90 days. The current evaluation store is one or more stores under the name of the target user;

[0069] S2 is the total inventory value of all products in the current evaluated store with an inventory age of 91-180 days;

[0070] S3 is the total inventory value of all products in the current evaluation store with an inventory age of 181-270 days;

[0071] a and b are constants, a = 0.8, b = 0.5;

[0072] M1 is the sales amount awaiting payment, which means the sales amount for which orders have been shipped but payment has not yet been received;

[0073] c is the repayment rate for the past six natural months starting from the current time;

[0074] M2 is the amount in transit, which indicates the amount that has been paid by the e-commerce platform but has not yet entered the target user's receiving account;

[0075] M3 is the reserved amount, which represents the amount reserved in the target user's receiving account to pay for potential or existing transaction disputes.

[0076] It should be noted that the term "repayment" in this application refers to the payment from the buyer to the target user (seller)'s payment account. The "repayment rate" for the past six natural months refers to the ratio of the repayment amount to the sales amount for the past six natural months.

[0077] S104: If the asset evaluation value is less than the target user's loan amount, the target user is identified as a risky loan user, and a corresponding risk control management strategy is generated.

[0078] In this embodiment of the present application, after evaluating the target user's store assets to obtain an asset assessment value, the asset assessment value is compared with the target user's outstanding loan amount, as this asset assessment value reflects the target user's future earning power and repayment ability. If the asset assessment value is less than the target user's outstanding loan amount, the target user is identified as a risky loan user, and a corresponding risk control management strategy is generated. Specifically, the target user is identified as having different risk levels based on the ratio of the asset assessment value to the outstanding loan amount, and different risk control management strategies are generated based on the different risk levels.

[0079] Furthermore, if the ratio of the asset assessment value to the loan amount is less than a first preset value, the target user is identified as a high-risk user and a heavy management policy is generated. If the ratio of the asset assessment value to the loan amount is less than a second preset value, the target user is identified as a medium-risk user and a moderate management policy is generated. If the second preset value is greater than the first preset value, the moderate management policy has a weaker control than the heavy management policy.

[0080] In one embodiment, the second preset value may be 0.5, and the first preset value may be 0.3. That is, when the asset evaluation value is lower than 30% of the loan amount, the target user is identified as a high-risk user, and the heavy management strategy generated at this time includes but is not limited to recommendations to freeze the target user's bank account and to deduct repayments in advance. When the asset evaluation value is lower than 50% of the loan amount, the target user is identified as a medium-risk user, and the moderate management strategy generated at this time includes but is not limited to requiring the target user to provide additional guarantee measures and strengthening the monitoring of the target user's operating conditions. In addition, if the asset evaluation value is slightly lower than the loan amount, it means that the target user's repayment ability has a low risk. At this time, risk warning information is generated, such as: sending a warning message to the financial institution suggesting the adoption of risk management.

[0081] In an embodiment of the present application, the store data of the target user is obtained from the e-commerce platform through an API interface, the store data is processed into derivative indicators, and then the asset evaluation value of the target user is obtained through a store asset value evaluation model (preset algorithm) that can be adopted by financial institutions. Finally, the ratio between the asset evaluation value and the target user's loan amount is used to generate a loan risk management strategy for the target user (cross-border e-commerce seller / enterprise) to solve the problem of difficulty in monitoring the loan risks of cross-border e-commerce enterprises.

[0082] like Figure 2 As shown, the embodiment of the present application further provides a risk control device based on store asset evaluation, including:

[0083] The data acquisition module 201 is used to obtain the store data of the target user from the e-commerce platform through the API interface;

[0084] A derivative index calculation module 202 is used to calculate derivative indicators on the store data to generate evaluation data;

[0085] The asset evaluation module 203 is used to obtain an asset evaluation value based on the evaluation data and a preset algorithm;

[0086] The risk control module 204 is configured to identify the target user as a risky loan user if the asset evaluation value is less than the target user's loan amount, and generate a corresponding risk control management strategy.

[0087] The risk control device based on store asset evaluation in the embodiment of the present application can be composed of a software module of the aforementioned system platform, loading the technical features provided by any one of the aforementioned method embodiments, to realize the processing of the store asset data of the target user to evaluate the asset value of the target user, and further generate a corresponding risk control management strategy based on the ratio of the target user's loan amount to the asset value.

[0088] The embodiment of the present application also provides a risk control system based on store asset evaluation, including an API interface calling module, a main control module and a financial institution docking module, wherein:

[0089] The API interface calling module connects to the API data interface of the e-commerce platform to obtain the store data of the e-commerce platform;

[0090] The main control module executes the technical steps corresponding to any of the aforementioned method embodiments;

[0091] The financial institution docking module is used to send risk control management strategies to the target user's loan amount institution.

[0092] It should be noted that the risk control system based on store asset evaluation here can be understood as a software system platform developed based on the risk control method based on store asset evaluation mentioned above, which realizes the same functions as the method embodiment and achieves the same technical effects.

[0093] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the technical processing steps provided in any of the aforementioned method embodiments are implemented.

[0094] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0095] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, or of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiment.

[0096] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "comprise", "include", "contain" and "have" are inclusive and therefore specify the presence of stated features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the specific order described or illustrated, unless the order of execution is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0097] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A risk control method based on store asset evaluation, characterized in that: The method comprises: Obtain the target user's store data from the e-commerce platform through the API interface; Calculating derivative indicators on the store data to generate evaluation data; Obtaining an asset evaluation value according to the evaluation data and a preset algorithm; If the asset evaluation value is less than the target user's loan amount, the target user is identified as a risky loan user and a corresponding risk control management strategy is generated.

2. The method according to claim 1, characterized in that The preset algorithm is: Asset evaluation value = (S1+S2*a+S3*b+M1)*c+M2+M3, where: S1 is the total inventory value of all products in the current evaluation store with an inventory age of 0-90 days. The current evaluation store is one or more stores under the name of the target user; S2 is the total inventory value of all products in the current evaluation store with an inventory age of 91-180 days; S3 is the total inventory value of all products in the current evaluation store with an inventory age of 181-270 days; a and b are constants, a = 0.8, b = 0.5; M1 is the sales amount to be paid, which means the sales amount for which the orders have been shipped but the payment has not been paid yet; c is the collection rate of the past six natural months starting from the current time; M2 is the amount in transit, which means the amount that has been paid by the e-commerce platform but has not yet entered the target user's payment account; M3 is the reserved reserve amount, which means the amount reserved in the target user's receiving account to pay for potential or existing transaction dispute-related amounts.

3. The method according to claim 1, characterized in that The store data includes at least inventory reports, sales orders and payment records, and the derivative indicator calculation includes: Counting the inventory quantity of each product code from the inventory report, and then summarizing to obtain the inventory data of the total product code of the store; Calculate all quantity-related indicators based on the time dimension, including at least the payment amount in the past six natural months from the current time; Summarize based on user dimensions, including at least: calculating the total collection amount of all stores authorized by the target user in the past 6 natural months starting from the current time and the inventory value of all inventory of the target user.

4. The method according to claim 1, characterized in that: After obtaining the store data of the target user from the e-commerce platform through the API interface, the method further includes: Performing data cleaning on the store data to remove invalid data and abnormal data; Convert the cleaned data into a data format that is easy to interpret and store.

5. The method according to any one of claims 1 to 4, characterized in that: If the asset evaluation value is less than the target user's loan amount, the target user is identified as a risky loan user, and a corresponding risk control management strategy is generated, including: The target users are identified as different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels.

6. The method according to claim 5, characterized in that The target user is identified as having different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels, including: If the ratio of the asset evaluation value to the loan amount is less than a first preset value, the target user is identified as a high-risk user and a heavy management strategy is generated.

7. The method according to claim 5, characterized in that The target user is identified as having different risk levels according to the ratio of the asset evaluation value to the loan amount, and different risk control management strategies are generated according to the different risk levels, including: If the ratio of the asset assessment value to the loan amount is less than a second preset value, the target user is identified as a medium-risk user and a moderate management strategy is generated, wherein the second preset value is greater than the first preset value, and the control strength of the moderate management strategy is weaker than that of the heavy management strategy.

8. A risk control device based on store asset evaluation, characterized in that: The device comprises: The data acquisition module is used to obtain the store data of the target user from the e-commerce platform through the API interface; A derivative indicator calculation module, used to calculate the derivative indicators of the store data to generate evaluation data; An asset evaluation module, used to obtain an asset evaluation value based on the evaluation data and a preset algorithm; The risk control module is used to identify the target user as a risky loan user if the asset evaluation value is less than the loan amount of the target user, and generate a corresponding risk control management strategy.

9. A risk control system based on store asset evaluation, characterized in that: The system includes an API interface calling module, a main control module and a financial institution docking module, wherein: The API interface calling module obtains the store data of the e-commerce platform by connecting with the API data interface of the e-commerce platform; The main control module executes the method described in any one of claims 1 to 7; The financial institution docking module is used to send risk control management strategies to the loan amount institution of the target user.

10. A storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the method according to any one of claims 1 to 7.

Images