Repayment risk prediction method and system based on financial credit business

Abstract

The invention relates to a repayment risk prediction method and system based on financial credit business, and the method comprises the steps: obtaining the asset income and expenditure information and loan record data of a loan user, carrying out the data desensitization transcoding, and carrying out the data association processing, and obtaining the income and expenditure associated data of the loan user, carrying out repayment feature correlation analysis on the bank flow of the loan user, analyzing a repayment feature association relationship of the loan user according to a correlation degree between repayment features, and obtaining historical repayment data of the loan user; and performing data training on the historical repayment data and the repayment feature association relationship, constructing a repayment risk prediction model when the loan user performs the credit service, obtaining an expected loan amount of the loan user, inputting the expected loan amount into the repayment risk prediction model, performing repayment risk prediction processing on the current credit service, and obtaining a repayment risk prediction result. And obtaining a current loan repayment risk prediction result of the loan user. The method has the effect of improving the repayment risk prediction accuracy of the financial credit business.

Description

Technical Field

[0001] The present application relates to the technical field of financial credit, and in particular to a repayment risk prediction method and system based on financial credit business. Background Art

[0002] At present, the credit business is developing rapidly, and various loan businesses such as commercial loans, micro loans, credit cards, etc. can be seen everywhere, which greatly facilitates daily capital turnover, but at the same time also exposes higher credit risks. Therefore, the credit business needs to be further managed.

[0003] The existing repayment risk prediction method for financial credit business is usually to evaluate the financial information provided by the borrower at the time of loan. However, during the repayment period, the borrower's financial changes or changes in repayment willingness will cause great risks to subsequent repayments. Financial institutions cannot fully understand the borrower's risk level, or there is a significant lag in the grasp of relevant information, which may lead to a deviation between the risk assessment and the actual repayment ability of the financial institution during the loan process, resulting in financial losses, etc., affecting the recovery of funds by the financial institution. Therefore, it is necessary to further optimize the repayment risk prediction method for financial credit business. Summary of the invention

[0004] In order to improve the accuracy of repayment risk prediction for financial credit business, the present application provides a repayment risk prediction method and system based on financial credit business.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: A repayment risk prediction method based on financial credit business, comprising: Acquire the asset income and expenditure information and loan record data of the loan user, perform data desensitization transcoding and data association processing on the asset income and expenditure information and the loan record data, and obtain the income and expenditure association data of the loan user; Based on the income and expenditure correlation data, the loan user's bank flow is analyzed for repayment feature correlation, and the loan user's repayment feature correlation relationship is analyzed based on the degree of correlation between the repayment features; Obtaining historical repayment data of loan users, performing data training on the correlation relationship between the historical repayment data and the repayment characteristics, and constructing a repayment risk prediction model for loan users when conducting credit business based on the training results; The expected loan amount of the loan user is obtained, the expected loan amount is input into the repayment risk prediction model, the repayment risk prediction process is performed on the current credit business, and the current loan repayment risk prediction result of the loan user is obtained.

[0006] In a preferred example, the present application may be further configured as follows: the historical repayment data of the loan user is obtained, the historical repayment data and the repayment feature association relationship are trained, and a repayment risk prediction model for the loan user when performing credit business is constructed according to the training result, specifically including: Obtain the historical repayment data of the loan user, perform repayment feature fitting processing on the historical repayment data and the repayment feature association relationship, and obtain the repayment feature difference corresponding to the historical loan business based on the fitting result; Obtain the balance data of historical loan business, analyze the repayment capacity of historical loan business, associate the repayment capacity analysis results with the corresponding repayment characteristic differences, and build a repayment risk prediction model for credit business.

[0007] By adopting the above technical solution, the data related to the credit business is converted into the same format through the desensitizing and transcoding preprocessing of the loan user's asset income and expenditure information and loan record data, and data association is performed to improve the correlation between data. The user's bank flow is analyzed for the correlation of repayment characteristics through the income and expenditure association data, so as to further analyze the correlation relationship of the loan user's repayment characteristics, which helps to improve the correlation between repayment characteristics, and the repayment characteristic correlation relationship is trained with historical repayment data as a parameter, so as to construct a repayment risk prediction model related to the credit business, and the credit data of the loan user is uniformly managed. In combination with the user's expected loan amount, the repayment risk of the current credit business is predicted, so as to obtain a comprehensive prediction of the user's actual bank flow, historical repayment completion, etc., and improve the accuracy of the repayment risk prediction.

[0008] In a preferred example, the present application can be further configured as follows: the expected loan amount of the loan user is obtained, the expected loan amount is input into the repayment risk prediction model, and the repayment risk prediction process is performed on the current credit business to obtain the current loan repayment risk prediction result of the loan user, specifically including: Obtaining the expected loan amount of the loan user, performing feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtaining a repayment feature matching result; According to the repayment feature matching result, analyzing the repayment difference between the loan user's total repayment amount between the loan repayment and the new loan and the user's surplus assets, and evaluating the user's credit limit according to the repayment difference; The expected loan amount of the loan user is adjusted according to the credit limit assessment result, and the repayment risk prediction processing of the current credit business is performed according to the adjusted loan limit to obtain the current loan repayment risk prediction result of the loan user.

[0009] By adopting the above technical solution, feature correlation matching is performed in combination with the user's expected loan amount and the repayment feature association relationship in the model, and based on the repayment feature matching result, it is further analyzed whether the user's current income situation can be kept stable between the repayment loan and the new loan, thereby improving the accuracy of the user's credit limit assessment, and further adjusting the expected loan amount according to the user's credit limit assessment result, so that the actual loan amount is more adapted to the user's actual economic situation, thereby accurately predicting the repayment risk of the current credit business and improving the accuracy of the repayment risk prediction.

[0010] In a preferred example, the present application may be further configured as follows: performing a repayment feature correlation analysis on the bank flow of the loan user according to the income and expenditure correlation data, and analyzing the repayment feature correlation relationship of the loan user according to the correlation degree between the repayment features, specifically including: The income and expenditure associated data is processed by superimposing the income and expenditure indicator parameters with the bank flow of the loan user, and the income and expenditure indicator with the number of superpositions exceeding the preset value is selected according to the number of superpositions to obtain the repayment characteristic parameters corresponding to the bank flow; According to the repayment characteristic parameters, the correlation coefficient between the repayment characteristic parameters is calculated, the repayment characteristic correlation analysis is performed according to the correlation coefficient, and the repayment characteristic association relationship of the loan user is constructed according to the repayment characteristic correlation analysis result.

[0011] By adopting the above technical solution, the income and expenditure related data and the bank flow of the loan user are superimposed with the income and expenditure indicator parameters to extract the key income and expenditure indicators whose superposition times exceed the preset value, and the correlation coefficients of the extracted repayment feature parameters are calculated to further analyze the correlation between the repayment features, thereby improving the accuracy of constructing the repayment feature association relationship.

[0012] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: A repayment risk prediction system based on financial credit business, comprising: A data preprocessing module is used to obtain the asset income and expenditure information and loan record data of the loan user, perform data desensitization transcoding and data association processing on the asset income and expenditure information and the loan record data, and obtain the income and expenditure association data of the loan user; A data analysis module, for performing a repayment feature correlation analysis on the bank flow of the loan user based on the income and expenditure correlation data, and analyzing the repayment feature correlation relationship of the loan user based on the correlation degree between the repayment features; A model building module is used to obtain the historical repayment data of the loan user, perform data training on the association relationship between the historical repayment data and the repayment characteristics, and build a repayment risk prediction model for the loan user when conducting credit business according to the training results; The risk prediction module is used to obtain the expected loan amount of the loan user, input the expected loan amount into the repayment risk prediction model, perform repayment risk prediction processing on the current credit business, and obtain the current loan repayment risk prediction result of the loan user.

[0013] In a preferred example, the present application can be further configured as follows: the risk prediction module includes: The data matching submodule is used to obtain the expected loan amount of the loan user, perform feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtain a repayment feature matching result; A data evaluation submodule is used to analyze the repayment difference between the total repayment amount of the loan user between the repayment loan and the new loan and the user's surplus assets according to the repayment feature matching result, and evaluate the user's credit limit according to the repayment difference; The risk prediction submodule is used to adjust the expected loan amount of the loan user according to the credit limit assessment result, and to perform repayment risk prediction processing on the current credit business according to the adjusted loan limit to obtain the current loan repayment risk prediction result of the loan user.

[0014] By adopting the above technical solution, the data related to the credit business is converted into the same format through the desensitizing and transcoding preprocessing of the loan user's asset income and expenditure information and loan record data, and data association is performed to improve the correlation between data. The user's bank flow is analyzed for the correlation of repayment characteristics through the income and expenditure association data, so as to further analyze the correlation relationship of the loan user's repayment characteristics, which helps to improve the correlation between repayment characteristics, and the repayment characteristic correlation relationship is trained with historical repayment data as a parameter, so as to construct a repayment risk prediction model related to the credit business, and the credit data of the loan user is uniformly managed. In combination with the user's expected loan amount, the repayment risk of the current credit business is predicted, so as to obtain a comprehensive prediction of the user's actual bank flow, historical repayment completion, etc., and improve the accuracy of the repayment risk prediction.

[0015] On the third aspect, the above-mentioned purpose of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned repayment risk prediction method based on financial credit business when executing the computer program.

[0016] Fourthly, the above-mentioned purpose of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned repayment risk prediction method based on financial credit business.

[0017] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through the desensitization and transcoding preprocessing of the loan user's asset income and expenditure information and loan record data, the data related to the credit business is converted into the same format, and data association is performed to improve the correlation between the data. The user's bank flow is analyzed for the correlation of repayment characteristics through the income and expenditure association data, so as to further analyze the correlation relationship of the loan user's repayment characteristics, which is helpful to improve the correlation between the repayment characteristics. The historical repayment data is used as a parameter to train the repayment characteristic correlation relationship, so as to build a repayment risk prediction model related to the credit business, and the credit data of the loan user is uniformly managed. In combination with the user's expected loan amount, the repayment risk of the current credit business is predicted, so as to obtain a comprehensive prediction of the user's actual bank flow, historical repayment completion, etc., and improve the accuracy of repayment risk prediction; 2. Combine the expected loan amount of the user with the repayment feature correlation relationship in the model to perform feature correlation matching, and further analyze whether the user's current income situation can be kept stable between the repayment loan and the new loan based on the repayment feature matching results, so as to improve the accuracy of the user's credit limit assessment, and further adjust the expected loan amount according to the user's credit limit assessment results, so that the actual loan amount is more compatible with the user's actual economic situation, so as to accurately predict the repayment risk of the current credit business and improve the accuracy of repayment risk prediction; 3. Superimpose the income and expenditure indicator parameters of the income and expenditure related data with the bank flow of the loan user to extract the key income and expenditure indicators whose superposition times exceed the preset value, calculate the correlation coefficient of the extracted repayment feature parameters, and further analyze the correlation between the repayment features, so as to improve the accuracy of constructing the repayment feature association relationship. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of an implementation method of a repayment risk prediction method based on financial credit business in this embodiment.

[0019] Figure 2 This is a flowchart for implementing step S20 of a repayment risk prediction method based on financial credit business in this embodiment.

[0020] Figure 3 This is a flowchart for implementing step S30 of a repayment risk prediction method based on financial credit business in this embodiment.

[0021] Figure 4This is a flowchart for implementing step S40 of a repayment risk prediction method based on financial credit business in this embodiment.

[0022] Figure 5 This is a structural block diagram of a repayment risk prediction system based on financial credit business in this embodiment.

[0023] Figure 6 It is a schematic diagram of the internal structure of a computer device used to implement the repayment risk prediction method of this embodiment. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a repayment risk prediction method based on financial credit business, which specifically includes the following steps: S10: Obtain the asset income and expenditure information and loan record data of the loan user, desensitize and transcode the asset income and expenditure information and loan record data, and perform data association processing to obtain the loan user's income and expenditure association data.

[0026] Specifically, based on the personal information, bank statements, assets under the name, etc. provided by the customer, the asset income and expenditure information and loan record data of the loan user are obtained, and the asset income and expenditure information and loan record data are desensitized and transcoded using preset sensitive keywords and data transcoding formats to obtain desensitized data in a unified data format that hides personal private information. Data association is performed using time sequence or user ID as the connection point for data association to obtain the loan user's income and expenditure related data.

[0027] S20: Based on the income and expenditure correlation data, the repayment characteristics correlation analysis is performed on the bank flow of the loan user, and the repayment characteristics correlation relationship of the loan user is analyzed according to the correlation degree between the repayment characteristics.

[0028] Specifically, Figure 2 As shown, step S20 includes: S201: superimpose the income and expenditure index parameters on the income and expenditure associated data and the bank flow of the loan user, select the income and expenditure index whose number of superpositions exceeds a preset value according to the number of superpositions, and obtain the repayment characteristic parameters corresponding to the bank flow.

[0029] Specifically, the income and expenditure related data are superimposed with the income and expenditure indicator parameters of the loan user's bank statements, and the number of times the bank statements with the same income and expenditure indicators are used for repayment are compared, including salary income, number of salary payments, expenditure amount, number of expenditure orders, deposit amount, number of deposit orders, etc. The income and expenditure indicators with a superposition number exceeding 1 are used as the repayment characteristic parameters of the loan business corresponding to the bank statements.

[0030] S202: Calculate the correlation coefficient between the repayment characteristic parameters according to the repayment characteristic parameters, perform repayment characteristic correlation analysis according to the correlation coefficient, and construct a repayment characteristic association relationship of the loan user according to the repayment characteristic correlation analysis result.

[0031] Specifically, the correlation coefficient between the repayment features is calculated according to the repayment feature parameters. In this embodiment, the correlation coefficient between the repayment features is analyzed by plotting the repayment features into a heat map. In this embodiment, the correlation coefficient of the repayment features exceeding 0.5 indicates high correlation, and less than 0.5 indicates low correlation. Therefore, the repayment feature association relationship of the loan user can be constructed according to the repayment feature correlation analysis results. The attribute between the repayment features in this embodiment is the correlation coefficient.

[0032] S30: Obtain the historical repayment data of the loan user, perform data training on the correlation between the historical repayment data and repayment characteristics, and build a repayment risk prediction model for the loan user when conducting credit business based on the training results.

[0033] Specifically, Figure 3 As shown, step S30 includes: S301: Obtain the historical repayment data of the loan user, perform repayment feature fitting processing on the historical repayment data and the repayment feature association relationship, and obtain the repayment feature difference corresponding to the historical loan business according to the fitting result.

[0034] Specifically, the historical repayment data of the loan user is obtained based on the user's authorization and verification, the historical repayment data is matched with the repayment feature association relationship, the correlation coefficient between the matching repayment features is analyzed with the historical repayment data, the repayment feature is fitted according to the analysis results, and the repayment feature difference of the historical repayment data under the current correlation coefficient is calculated, so as to obtain the repayment feature difference corresponding to the historical loan business.

[0035] S302: Obtain the balance data of historical loan business, analyze the repayment capacity of historical loan business, associate the repayment capacity analysis results with the corresponding repayment characteristic difference, and build a repayment risk prediction model for the credit business.

[0036] Specifically, the historical repayment difference is calculated by subtracting the repayment amount from the bill amount of the historical loan business, and then judging whether the historical loan business has a surplus based on the historical repayment difference. When the historical repayment difference is greater than 0, the repayment ability of the current historical loan business is poor, and it is necessary to calculate the revolving interest for each period in combination with the corresponding repayment characteristic difference, and adjust the repayment amount corresponding to the repayment characteristic difference; when the historical repayment difference is less than or equal to 0, the repayment ability of the current historical loan business is strong, and it is necessary to adjust the corresponding repayment amount in combination with the corresponding repayment characteristic difference, so as to construct a repayment risk prediction model for the credit business based on the adjustment results and the correlation between the repayment characteristic difference and the repayment ability analysis results.

[0037] S40: Obtain the expected loan amount of the loan user, input the expected loan amount into the repayment risk prediction model, perform repayment risk prediction processing on the current credit business, and obtain the current loan repayment risk prediction result of the loan user.

[0038] Specifically, Figure 4 As shown, step S40 includes: S401: Obtain the expected loan amount of the loan user, perform feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtain a repayment feature matching result.

[0039] Specifically, the expected loan amount of the loan user is obtained, and the expected loan amount is matched with the total repayment feature association relationship of the repayment risk prediction model. The repayment feature with the highest correlation for each repayment period is selected from the repayment feature relationship, thereby obtaining the repayment feature matching result.

[0040] S402: Analyze the repayment difference between the total repayment amount of the loan user between the loan repayment and the new loan and the user's surplus assets according to the repayment feature matching result, and evaluate the user's credit limit according to the repayment difference.

[0041] Specifically, the loan user's total repayment amount between the repayment loan and the new loan is analyzed based on the repayment feature matching results to see whether it is within the customer's surplus assets, and the repayment difference between the total repayment amount of each period and the customer's surplus assets is calculated, so as to evaluate the user's credit limit based on the size of the repayment difference. In this embodiment, the larger the repayment difference, the smaller the customer's credit limit.

[0042] S403: adjusting the expected loan amount of the loan user according to the credit amount assessment result, and performing repayment risk prediction processing on the current credit business according to the adjusted loan amount to obtain the current loan repayment risk prediction result of the loan user.

[0043] Specifically, the expected loan amount of the loan user is adjusted according to the credit limit assessment result. For example, the worse the loan limit assessment result is, the lower the customer's loan limit is, and the better the loan limit assessment result is, the higher the customer's loan limit is. The repayment risk of the current credit business is predicted based on the adjusted loan limit. When the loan limit is within the customer's surplus range for each period, the repayment risk is small; when the loan limit is outside the customer's surplus range for each period, the repayment risk is large, thereby obtaining the loan user's current loan repayment risk prediction result.

[0044] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0045] In one embodiment, a repayment risk prediction system based on financial credit business is provided, and the repayment risk prediction system based on financial credit business corresponds one-to-one with the repayment risk prediction method based on financial credit business in the above embodiment. Figure 5 As shown, the repayment risk prediction system based on financial credit business includes a data preprocessing module, a data analysis module, a model building module and a risk prediction module. The detailed description of each functional module is as follows: The data preprocessing module is used to obtain the asset income and expenditure information and loan record data of the loan user, desensitize and transcode the asset income and expenditure information and loan record data, and perform data association processing to obtain the loan user's income and expenditure association data.

[0046] The data analysis module is used to perform a repayment feature correlation analysis on the bank flow of the loan user based on the income and expenditure correlation data, and analyze the repayment feature correlation relationship of the loan user based on the correlation degree between the repayment features.

[0047] The model building module is used to obtain the historical repayment data of loan users, conduct data training on the correlation between historical repayment data and repayment characteristics, and build a repayment risk prediction model for loan users when conducting credit business based on the training results.

[0048] The risk prediction module is used to obtain the expected loan amount of the loan user, input the expected loan amount into the repayment risk prediction model, perform repayment risk prediction processing on the current credit business, and obtain the current loan repayment risk prediction result of the loan user.

[0049] Preferably, the risk prediction module includes: The data matching submodule is used to obtain the expected loan amount of the loan user, perform feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtain the repayment feature matching result.

[0050] The data evaluation submodule is used to analyze the repayment difference between the total repayment amount of the loan user between the repayment loan and the new loan and the user's surplus assets according to the repayment feature matching results, and evaluate the user's credit limit according to the repayment difference.

[0051] The risk prediction submodule is used to adjust the expected loan amount of the loan user according to the credit limit assessment result, and to perform repayment risk prediction processing on the current credit business according to the adjusted loan limit to obtain the current loan repayment risk prediction result of the loan user.

[0052] Preferably, the data analysis module specifically includes: The feature screening submodule is used to perform superposition processing on the income and expenditure indicator parameters of the income and expenditure related data and the bank flow of the loan user, and select the income and expenditure indicators whose superposition times exceed the preset value according to the superposition times to obtain the repayment feature parameters corresponding to the bank flow.

[0053] The correlation analysis submodule is used to calculate the correlation coefficient between the repayment characteristic parameters according to the repayment characteristic parameters, perform repayment characteristic correlation analysis according to the correlation coefficient, and construct the repayment characteristic correlation relationship of the loan user according to the repayment characteristic correlation analysis result.

[0054] Preferably, the model building module specifically includes: The feature fitting submodule is used to obtain the historical repayment data of loan users, perform repayment feature fitting processing on the historical repayment data and the repayment feature association relationship, and obtain the repayment feature difference corresponding to the historical loan business based on the fitting results.

[0055] The model building submodule is used to obtain the balance data of historical loan business, analyze the repayment capacity of historical loan business, associate the repayment capacity analysis results with the corresponding repayment characteristic differences, and build a repayment risk prediction model for credit business.

[0056] For the specific definition of the repayment risk prediction system based on financial credit business, please refer to the definition of the repayment risk prediction method based on financial credit business mentioned above, which will not be repeated here. Each module in the above-mentioned repayment risk prediction system based on financial credit business can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0057] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store repayment risk prediction data for financial credit business. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a repayment risk prediction method based on financial credit business is implemented.

[0058] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a repayment risk prediction method based on financial credit business are implemented.

[0059] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0060] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0061] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A repayment risk prediction method based on financial credit business, characterized in that: include: Acquire the asset income and expenditure information and loan record data of the loan user, perform data desensitization transcoding and data association processing on the asset income and expenditure information and the loan record data, and obtain the income and expenditure association data of the loan user; Based on the income and expenditure correlation data, the loan user's bank flow is analyzed for repayment feature correlation, and the loan user's repayment feature correlation relationship is analyzed based on the degree of correlation between the repayment features; Obtaining historical repayment data of loan users, performing data training on the correlation relationship between the historical repayment data and the repayment characteristics, and constructing a repayment risk prediction model for loan users when conducting credit business based on the training results; The expected loan amount of the loan user is obtained, the expected loan amount is input into the repayment risk prediction model, the repayment risk prediction process is performed on the current credit business, and the current loan repayment risk prediction result of the loan user is obtained.

2. The repayment risk prediction method based on financial credit business according to claim 1 is characterized in that: The obtaining of the expected loan amount of the loan user, inputting the expected loan amount into the repayment risk prediction model, performing repayment risk prediction processing on the current credit business, and obtaining the current loan repayment risk prediction result of the loan user specifically includes: Obtaining the expected loan amount of the loan user, performing feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtaining a repayment feature matching result; According to the repayment feature matching result, analyzing the repayment difference between the loan user's total repayment amount between the loan repayment and the new loan and the user's surplus assets, and evaluating the user's credit limit according to the repayment difference; The expected loan amount of the loan user is adjusted according to the credit limit assessment result, and the repayment risk prediction processing of the current credit business is performed according to the adjusted loan limit to obtain the current loan repayment risk prediction result of the loan user.

3. The repayment risk prediction method based on financial credit business according to claim 1, characterized in that: The method of performing a repayment feature correlation analysis on the loan user's bank flow according to the income and expenditure correlation data and analyzing the repayment feature correlation relationship of the loan user according to the correlation between the repayment features specifically includes: The income and expenditure associated data is processed by superimposing the income and expenditure indicator parameters with the bank flow of the loan user, and the income and expenditure indicator with the number of superpositions exceeding the preset value is selected according to the number of superpositions to obtain the repayment characteristic parameters corresponding to the bank flow; According to the repayment characteristic parameters, the correlation coefficient between the repayment characteristic parameters is calculated, the repayment characteristic correlation analysis is performed according to the correlation coefficient, and the repayment characteristic association relationship of the loan user is constructed according to the repayment characteristic correlation analysis result.

4. The repayment risk prediction method based on financial credit business according to claim 1 is characterized in that: The obtaining of historical repayment data of the loan user, performing data training on the historical repayment data and the repayment feature association relationship, and constructing a repayment risk prediction model for the loan user when performing credit business according to the training result specifically includes: Obtain the historical repayment data of the loan user, perform repayment feature fitting processing on the historical repayment data and the repayment feature association relationship, and obtain the repayment feature difference corresponding to the historical loan business based on the fitting result; Obtain the balance data of historical loan business, analyze the repayment capacity of historical loan business, associate the repayment capacity analysis results with the corresponding repayment characteristic differences, and build a repayment risk prediction model for credit business.

5. A repayment risk prediction system based on financial credit business, characterized in that: include: A data preprocessing module is used to obtain the asset income and expenditure information and loan record data of the loan user, perform data desensitization transcoding and data association processing on the asset income and expenditure information and the loan record data, and obtain the income and expenditure association data of the loan user; A data analysis module, for performing a repayment feature correlation analysis on the bank flow of the loan user based on the income and expenditure correlation data, and analyzing the repayment feature correlation relationship of the loan user based on the correlation degree between the repayment features; A model building module is used to obtain the historical repayment data of the loan user, perform data training on the association relationship between the historical repayment data and the repayment characteristics, and build a repayment risk prediction model for the loan user when conducting credit business according to the training results; The risk prediction module is used to obtain the expected loan amount of the loan user, input the expected loan amount into the repayment risk prediction model, perform repayment risk prediction processing on the current credit business, and obtain the current loan repayment risk prediction result of the loan user.

6. The repayment risk prediction system based on financial credit business according to claim 5 is characterized in that: The risk prediction module includes: The data matching submodule is used to obtain the expected loan amount of the loan user, perform feature correlation matching processing on the expected loan amount and the repayment feature association relationship in the repayment risk prediction model, and obtain a repayment feature matching result; A data evaluation submodule is used to analyze the repayment difference between the total repayment amount of the loan user between the repayment loan and the new loan and the user's surplus assets according to the repayment feature matching result, and evaluate the user's credit limit according to the repayment difference; The risk prediction submodule is used to adjust the expected loan amount of the loan user according to the credit limit assessment result, and to perform repayment risk prediction processing on the current credit business according to the adjusted loan limit to obtain the current loan repayment risk prediction result of the loan user.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the repayment risk prediction method based on financial credit business as described in any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the repayment risk prediction method based on financial credit business as described in any one of claims 1 to 4 are implemented.

Images