Method and system for determining debt paying stability of credit user

Abstract

The invention discloses a method and system for determining debt paying stability of a credit user, and the method comprises the steps: collecting the multi-dimensional information of a borrower, and the multi-dimensional information comprises basic information, credit investigation data and third-party data; analyzing and processing the collected data to obtain subitems capable of reflecting borrower qualification, customer group stability, multi-debt joint degree trend and debt pressure trend; extracting stability prediction variables in the multi-dimensional information, and inputting the variables into a preset model to obtain a debt paying stability coefficient of the target user; and verifying the rationality and consistency of the debt paying stability coefficient on a risk sample with a long performance period. By deeply integrating and analyzing the multi-dimensional information of the borrower, the credit status, economic ability and behavior pattern of the borrower can be comprehensively and deeply known, so that a credit institution can more quickly identify potential low-risk and high-value customers, and meanwhile, the institution is helped to more effectively predict and avoid potential risk points.

Description

Technical Field

[0001] The present invention belongs to the field of financial technology and relates to a method and system for determining the debt repayment stability of a credit user. Background Art

[0002] With the booming consumer finance industry, competition among financial institutions has become increasingly fierce, and credit business has become an important force in promoting financial development. However, while enjoying convenient financial services, credit users are also facing the risks of multiple debts and excessive credit. Excessive credit may cause borrowers to fall into repayment difficulties, increase the probability of default, and may also pose a serious threat to the asset quality and market stability of financial institutions. Therefore, regulators have put forward higher requirements for the risk management capabilities of financial institutions, emphasizing the need to establish a comprehensive and effective risk management framework to scientifically and rationally assess the debt repayment ability of credit users and strictly control credit limits, so as to maintain the fairness, transparency and stability of the financial market.

[0003] In the retail credit business of traditional commercial banks, the assessment of the stability of the borrower's debt repayment ability mainly depends on the nature of their work and the stability of their career. Financial institutions will carefully examine the operating conditions, industry status, development trends and the stability of the borrower's past income of the company where the borrower works, and use this as an important basis for judging their debt repayment ability. At the same time, they will also pay attention to the borrower's years of work, position level, staff establishment and other professional factors, and verify them through work income certificates, tax payment records, social security and provident fund payment records, etc.

[0004] However, this traditional assessment method has many defects. First, the review conditions and factors are too stringent, which often leads to the exclusion of some borrowers with good credit but not meeting specific conditions, limiting the popularity of credit services. Secondly, the review granularity is large, and it is impossible to capture the individual differences and potential risks of borrowers in detail. Moreover, the review dimension is single, mainly focusing on the borrower's work and career information, ignoring other factors that may affect debt repayment ability, such as family status, consumption habits, external liabilities, etc. Finally, the coverage is narrow, and it is difficult to fully reflect the borrower's overall credit status and debt repayment ability.

[0005] In view of the above problems, it is necessary to develop a more scientific, comprehensive and objective method for assessing the economic capacity of credit users, so as to accurately determine the credit limit range of credit users and implement credit limit management in a scientific and reasonable manner. The borrower's debt repayment ability, stability, and factors such as the effective period of exposure and the repayment cycle after the IOU is generated should be comprehensively considered to improve the risk management level of financial institutions and ensure the healthy and stable development of the financial market. Summary of the invention

[0006] The purpose of the present invention is to solve the problem of poor accuracy of the approval method in the prior art and to provide a method and system for determining the debt repayment stability of a credit user.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A method for determining the debt repayment stability of a credit user comprises the following steps: Collecting multi-dimensional information of borrowers, including basic information, credit data and third-party data; Analyze and process the collected data to obtain sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt trends and debt pressure trends; Extracting stability prediction variables from the multi-dimensional information, and inputting these variables into a preset model to obtain a debt repayment stability coefficient of the target user; The rationality and consistency of the debt repayment stability coefficient are verified on risk samples with long performance cycles.

[0008] The collected data is analyzed and processed, specifically: Assess the borrower's basic qualifications, including occupation and income asset structure, social relations and social status, and financial institution evaluation; Assess the borrower's customer base stability, including address stability, career stability and growth, and asset holding stability; Analyze the trend of multiple debts of borrowers, including the changing trend of credit application frequency; Assess the borrower's debt stress trend, including the flow trajectory of credit pools and debt concentration.

[0009] The basic qualifications of the borrower to be assessed include: Review the borrower's marital status and education level, and cross-check the self-filled information with the verified information; verify the borrower's professional background, assess the stability of his / her industry and the reliability of his / her income source; analyze the borrower's asset structure, including fixed assets and current assets, and assess his / her overall wealth status and debt repayment ability; Describe the social relationship map and indirectly reflect the borrower's social environment by evaluating the contact's credit qualifications and post-loan performance; Analyze the loan contract information on the borrower's credit report, including the contract amount, repayment method, loan term and loan pricing, to evaluate the financial institution's evaluation of the borrower.

[0010] The evaluation of the borrower's customer base stability is specifically as follows: Assess address stability based on the aggregation and dispersion of the borrower's registered address, permanent residence address, LBS application address, and mobile phone number address; Assess career stability and growth based on the number of companies employed, length of employment, and the match between income and age; Assess asset holding stability based on the borrower's RV property purchase and holding period, RV loan repayment status and remaining term.

[0011] The analysis of the borrower's multiple debt trend is as follows: Obtain the changing trend of the borrower's credit application frequency, and judge the change of the borrower's capital hunger by combining the difference of risk statistical parameters; The K-means clustering algorithm is used to count the number of applications, and the slope and intercept of two adjacent application peaks are calculated to evaluate the speed of change of long-term co-debt.

[0012] The assessment of the debt pressure trend of the borrower is specifically as follows: By comparing the loan information in two cross-time zone PBOC personal credit information reports, the target user's credit fund outflow and inflow are evaluated; Analyze debt concentration to determine whether the borrower is an active account master or a passive account master.

[0013] The debt repayment stability coefficient is calculated by the following formula: Debt repayment stability coefficient = ∑(basic qualifications * customer base stability * multiple debt degree trend * debt pressure trend).

[0014] The rationality and consistency of the debt repayment stability coefficient is verified on the risk sample with a long performance cycle, specifically: Divide the borrower population into multiple gradients based on risk statistical parameter values, each gradient represents a different risk level; Within each gradient, the average or median of the debt repayment stability coefficient is calculated to assess the overall debt repayment stability of borrowers within the gradient; Compare the differences in debt repayment stability coefficients between different gradients to verify whether they are consistent with the gradient change trend of the risk statistical parameters, so as to confirm the consistency of the strength of stability and the gradient of risk statistical parameters among the borrowing groups.

[0015] A system for determining the stability of a credit user's debt repayment comprises the following modules: A multi-dimensional information collection module, which is used to collect multi-dimensional information of the borrower, wherein the multi-dimensional information includes at least basic information, credit data and third-party data; A data analysis and processing module, which is used to analyze and process the collected multi-dimensional data, and extract sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt degree trends, and debt pressure trends; A stability prediction variable extraction and model input module, wherein the stability prediction variable extraction and model input module extracts stability prediction variables from the multi-dimensional information after parsing and processing; the extracted stability prediction variables are input into a preset model, and the model is trained and optimized to calculate the debt repayment stability coefficient of the target user based on the input variables; A debt repayment stability coefficient verification module is used to verify the rationality and consistency of the debt repayment stability coefficient on risk samples.

[0016] The system also includes an output and feedback module, which is used to output the calculated debt repayment stability coefficient and credit decision suggestions based on the coefficient; receive feedback from credit business personnel for continuous optimization and improvement of the system.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The method for determining the debt repayment stability of credit users in the present invention, through deep integration and analysis of the multi-dimensional information of borrowers, covers basic information, credit records and third-party data sources, so as to fully and deeply understand the credit status, economic ability and behavior patterns of borrowers. By extracting key stability prediction variables and inputting these variables into the preset model, the debt repayment stability coefficient of each target user can be accurately calculated. The accuracy and efficiency of credit decision-making are greatly improved, so that credit institutions can more quickly identify potential low-risk and high-value customers, and at the same time, the risk management capabilities of credit business are significantly enhanced, helping institutions to more effectively predict and avoid potential risk points. In addition, the method also ensures the rationality and consistency of the debt repayment stability coefficient through continuous verification and optimization in actual business, laying a solid foundation for the sustainable development of credit business. Finally, by providing borrowers with more personalized and accurate credit services, the user experience and satisfaction are effectively improved, the trust and cooperative relationship between credit institutions and borrowers is further enhanced, and the healthy development of the entire credit market is promoted. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 The present invention is a flow chart of the method for determining the debt repayment stability of a credit user. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0023] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1 , the flow chart of the method for determining the stability of debt repayment of a credit user of the present invention comprises the following steps: S1, collect multi-dimensional information of the borrower, wherein the multi-dimensional information includes basic information, credit data and third-party data.

[0024] S2, analyzes and processes the collected data to obtain sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt level trends and debt pressure trends.

[0025] S2.1, assess the borrower’s basic qualifications, including occupation and income-asset structure, social relations and social status, and financial institution evaluation.

[0026] S2.1.1, review the borrower's marital status and educational level, and cross-check the self-filled information with the verified information; verify the borrower's professional background, assess the stability of his or her industry and the reliability of his or her income source; analyze the borrower's asset structure, including fixed assets and current assets, and assess his or her overall wealth status and debt repayment ability.

[0027] S2.1.2, depicts the social relationship map, and indirectly reflects the borrower's social environment by evaluating the contact's credit qualifications and post-loan performance.

[0028] S2.1.3, parse the loan contract information on the borrower’s credit report, including the contract amount, repayment method, loan term and loan pricing, to assess the financial institution’s evaluation of the borrower.

[0029] S2.2, evaluate the borrower’s customer base stability, including address stability, career stability and growth, and asset holding stability.

[0030] S2.2.1, address stability is assessed based on the degree of aggregation and dispersion of the borrower’s registered residence address, permanent residence address, LBS application address, and mobile phone number address.

[0031] S2.2.2, assess career stability and growth potential based on the number of companies employed, length of employment, and the match between income and age.

[0032] S2.2.3, assess the stability of asset holdings based on the borrower’s RV property purchase and holding period, the repayment status of the RV loan, and the remaining term.

[0033] S2.3, analyze the trend of multiple debt levels of borrowers, including the changing trend of credit application frequency.

[0034] S2.3.1, obtain the changing trend of the borrower's credit application frequency, and combine the differences in risk statistical parameters to determine the changes in the borrower's capital hunger.

[0035] S2.3.2, use K-means clustering algorithm to count the number of applications, and calculate the slope and intercept of two adjacent application peaks to evaluate the speed of change of multi-share debt.

[0036] S2.4, assess the borrower's debt pressure trend, including the flow trajectory of credit funds pool and debt concentration.

[0037] S2.4.1, by comparing the loan information in two cross-time zone PBOC credit reports, assess the target user's credit fund outflow and inflow; S2.4.2, analyze the debt concentration to determine whether the borrower is an active account master or a passive account master.

[0038] S3, extracting stability prediction variables from the multi-dimensional information, and inputting these variables into a preset model to obtain the debt repayment stability coefficient of the target user.

[0039] Debt repayment stability coefficient = ∑(basic qualifications * customer base stability * multiple debt degree trend * debt pressure trend).

[0040] S4. Verify the rationality and consistency of the debt repayment stability coefficient on risk samples with a long performance cycle.

[0041] S4.1, divide the borrower population into multiple gradients based on the risk statistical parameter values, each gradient represents a different risk level.

[0042] S4.2. Within each gradient, calculate the average or median of the debt repayment stability coefficient to assess the overall debt repayment stability of borrowers within that gradient.

[0043] S4.3, compare the differences in debt repayment stability coefficients between different gradients to verify whether they are consistent with the gradient change trend of the risk statistical parameters, so as to confirm the consistency of the strength of stability and the gradient of risk statistical parameters among the borrowing groups. Example

[0044] Debt repayment stability is used as a predictive variable in the decision-making of credit line exposure approval. Its main function is to make up for the defect of "determining the debt repayment ability in a certain period in the future based on the borrower's economic ability at a certain point in time". By extracting multi-dimensional features such as basic qualifications, customer base stability, multi-debt degree trend, and debt pressure trend into the model device, a scientific and quantitative prediction and ranking is adopted for the borrower's future qualification stability, risk resistance cycle ability, and cash flow supply and demand balance stability. The debt repayment stability coefficient is not only the sustainable length of debt repayment ability, but also the credibility of the economic ability at a certain point in time reflecting the economic ability in a certain period in the future.

[0045] Debt repayment stability coefficient = ∑ (basic qualifications * customer base stability * multi-debt degree trend * debt pressure trend) 1. Basic qualifications The borrower's basic qualifications are mainly reflected in three aspects: occupation and income asset structure, social relations and social status, and financial institution evaluation, which correspond to their own debt repayment ability, non-financial institution capital turnover ability and financial institution capital turnover ability respectively.

[0046] In addition to investigations into marital status and educational level, and cross-comparison of self-filled information with verified information, the assessment of social relations and social status also focuses on the depiction of the social relationship map, mapping the borrower's social environment through the evaluation of the contact's credit qualifications and post-loan performance.

[0047] The evaluation of financial institutions is mainly carried out through the analysis of factors such as the contract amount, repayment method, loan term, loan pricing, etc. of the loan contract on the borrower's credit report. It is generally believed that borrowers who obtain higher amounts, longer terms, lower pricing and repayment of principal on maturity are more favored by financial institutions.

[0048] The contract amount, repayment method, and loan term can all be directly mapped from the information fields of a single loan contract; the calculation of loan pricing involves personalized parsing logic: in terms of the choice of time window, you can choose the entire loan contract and convert "(monthly repayment amount*total term-contract amount) / contract amount" according to the annualized capital utilization rate to get it, or you can choose the second half of the loan contract and convert "(monthly repayment amount*remaining term-remaining loan balance) / remaining loan balance" according to the annualized capital utilization rate to get it. The combination of the two algorithms can effectively reduce the calculation error caused by irregular repayment methods or partial early settlement; in the processing of loan contract types, due to the clear items of a single loan note, the pricing calculation of the two types of loan contracts under non-revolving loans and revolving credits is relatively accurate and close to the actual execution pricing. There are multiple long and short loan note contracts reported under revolving loans, which causes the pricing calculation to deviate from the actual execution pricing. In terms of strategy, the absolute value of the inferred pricing is weakened and the ranking and relative position of the pricing are focused on.

[0049] 2. Customer base stability The first is address stability. According to the degree of aggregation and dispersion of the borrower's registered address, permanent residence address, LBS application address, and mobile phone number address, the longest distance between any addresses is used to describe the borrower's address movement radius, and further determine whether the borrower is long-term and fixed in economically developed areas or central cities, or whether he or she meets the activity trajectory characteristics of short-term migrant workers. The second is career stability and growth, which is assessed based on the number of companies employed, length of employment, and the degree of match between income and age. The third is asset holding stability, which is assessed based on the purchase and holding time of the borrower's RV property, the repayment status of the RV loan, and the remaining term.

[0050] Career stability growth coefficient = career stability coefficient * income growth coefficient. The fewer the number of employment companies and the longer the average length of employment, the higher the career stability coefficient; "personal income / average income of the same age group" is used as the income growth coefficient. The higher the ratio, the faster the growth.

[0051] Asset stability coefficient = holding time coefficient * associated loan repayment coefficient. The earlier the asset purchase time is calculated from the contract generation time of the associated loan, and the longer the normal repayment period is, the more stable the target user's holding of the asset is.

[0052] 3. Trend of long-term debt Based on the changing trend of the borrower's credit application frequency and the difference in risk statistical parameters, we can judge the change in the borrower's capital hunger. Borrowers whose application frequency increases rapidly will have increased debt and a faster deterioration in qualifications in the future, and their future debt repayment stability will be poor. The intercept introduced later can quantify the speed of the increase in the target user's application frequency.

[0053] The data sources for observing the frequency of borrowers' credit business applications include the approval query records of the People's Bank of China's credit investigation and the approval query times of non-bank institutions on the third-party data platform. Based on the query details, the K-means clustering algorithm is used to obtain a series of application frequency statistics for different time periods, including the mean / extreme value / standard deviation / peak and trough numbers, to describe the changes in the average monthly number of applications of target users, the proportion of recent applications in a period of time, and whether the application behavior has periodic and concentrated characteristics.

[0054] Take any two adjacent application number peaks as two observation points, that is, point to the two adjacent capital demand outbreak points of the borrower, and use a simple linear function to calculate the slope and intercept of the two application number peaks. The slope can more effectively reflect the changing speed of the target user's long-term co-debt, and "small slope and large intercept" may be a fixed high-long feature of specific regions and specific target users. The application of the slope has largely corrected the judgment bias of long-term attention to the intercept.

[0055] A simple linear function A=(YX) / B, where X and Y are two consecutive application number peaks, B is the interval between the two application number peaks, A is the slope, and X and Y are the two intercepts.

[0056] 4. Debt pressure trend Based on the target user's multi-node credit behavior, multiple cross-time zone personal credit information reports from the People's Bank of China are obtained. By refining and aggregating migration trend features, the target user's debt pressure change trend is characterized, and the target user's past credit fund flow patterns and future credit health are further evaluated.

[0057] (1) Flow track of credit fund pool By distinguishing the time points of the two credit reports, the loans generated before the first credit report are defined as existing liabilities, and the loans generated between the two credit reports are defined as new liabilities. By comparing the difference between the total amount of new liabilities and the balance of existing liabilities in the two credit reports, we can derive the relationship between the outflow and inflow of the target user's credit funds. When the outflow is much greater than the inflow, it indicates that the target user is a borrower who is deeply trapped in the quagmire. On the contrary, when the outflow is much less than the inflow, it indicates that the target user is a borrower who has landed.

[0058] The velocity ratio of the personal credit fund pool = (fund outflow - fund inflow) / interval duration. If the velocity ratio is greater than 0, it indicates that the target user is a borrower who is stuck in the quagmire. If the velocity ratio is less than 0, it indicates that the target user is a borrower who is getting ashore. The larger the absolute value of the velocity ratio, the more the target user conforms to the inference direction.

[0059] (2) Debt concentration For borrowers whose liabilities increase between two credit reports, the liability growth is concentrated in a few institutions or credit agreements. If the number of application approval inquiries between the two credit reports is very small, it indicates that the borrower is a target user who mainly uses active accounts; if the number of application approval inquiries between the two credit reports is relatively large, it indicates that the borrower is a target user who mainly uses passive accounts, and the more application approval inquiries, the more the target user conforms to the inference direction, and the application during the period may be rejected or the credit limit may be low, and the probability of default of such target users in the future may rise rapidly.

[0060] Through multi-dimensional research on basic qualifications, customer stability, multiple debt trends, and debt pressure trends, combined with differences in risk statistical parameters, we confirm the stability evaluation factor of the target user in each dimension, and ultimately derive the debt repayment stability coefficient. The product of this coefficient and the debt repayment ability at a certain point in time constitutes an important module for credit limit decision-making.

[0061] In verifying the rationality of the debt repayment stability coefficient, on the one hand, we focus on the consistency between the strength of stability and the gradient of risk statistical parameters of the borrowing population; on the other hand, whether the strength of stability is consistent with the step-length convergence of the statistical parameter gradient after extending the account period is also an important acceptance indicator.

[0062] An embodiment of the present invention is a system for determining the stability of a credit user's debt repayment, comprising the following modules: A multi-dimensional information collection module, which is used to collect multi-dimensional information of the borrower, wherein the multi-dimensional information includes at least basic information, credit data and third-party data; A data analysis and processing module, which is used to analyze and process the collected multi-dimensional data, and extract sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt degree trends, and debt pressure trends; A stability prediction variable extraction and model input module, wherein the stability prediction variable extraction and model input module extracts stability prediction variables from the multi-dimensional information after parsing and processing; the extracted stability prediction variables are input into a preset model, and the model is trained and optimized to calculate the debt repayment stability coefficient of the target user based on the input variables; A debt repayment stability coefficient verification module is used to verify the rationality and consistency of the debt repayment stability coefficient on risk samples.

[0063] The output and feedback module is used to output the calculated debt repayment stability coefficient and the credit decision suggestion based on the coefficient; receive feedback from the credit business personnel for continuous optimization and improvement of the system.

[0064] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining the stability of a credit user's debt repayment, characterized in that: The following steps are involved: Collecting multi-dimensional information of borrowers, including basic information, credit data and third-party data; Analyze and process the collected data to obtain sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt trends and debt pressure trends; Extracting stability prediction variables from the multi-dimensional information, and inputting these variables into a preset model to obtain a debt repayment stability coefficient of the target user; The rationality and consistency of the debt repayment stability coefficient are verified on risk samples with long performance cycles.

2. A method for determining the debt repayment stability of a credit user as claimed in claim 1, characterized in that: The collected data is analyzed and processed, specifically: Assess the borrower's basic qualifications, including occupation and income asset structure, social relations and social status, and financial institution evaluation; Assess the borrower's customer base stability, including address stability, career stability and growth, and asset holding stability; Analyze the trend of multiple debts of borrowers, including the changing trend of credit application frequency; Assess the borrower's debt stress trend, including the flow trajectory of credit pools and debt concentration.

3. A method for determining the debt repayment stability of a credit user as claimed in claim 2, characterized in that: The basic qualifications of the borrower to be assessed include: Review the borrower's marital status and education level, and cross-check the self-filled information with the verified information; verify the borrower's professional background, assess the stability of his / her industry and the reliability of his / her income source; analyze the borrower's asset structure, including fixed assets and current assets, and assess his / her overall wealth status and debt repayment ability; Describe the social relationship map and indirectly reflect the borrower's social environment by evaluating the contact's credit qualifications and post-loan performance; Analyze the loan contract information on the borrower's credit report, including the contract amount, repayment method, loan term and loan pricing, to evaluate the financial institution's evaluation of the borrower.

4. A method for determining the debt repayment stability of a credit user as claimed in claim 2, characterized in that: The evaluation of the borrower's customer base stability is specifically as follows: Assess address stability based on the aggregation and dispersion of the borrower's registered address, permanent residence address, LBS application address, and mobile phone number address; Assess career stability and growth based on the number of companies employed, length of employment, and the match between income and age; Assess asset holding stability based on the borrower's RV property purchase and holding period, RV loan repayment status and remaining term.

5. A method for determining the debt repayment stability of a credit user as claimed in claim 1, characterized in that: The analysis of the borrower's multiple debt trend is as follows: Obtain the changing trend of the borrower's credit application frequency, and judge the change of the borrower's capital hunger by combining the difference of risk statistical parameters; The K-means clustering algorithm is used to count the number of applications, and the slope and intercept of two adjacent application peaks are calculated to evaluate the speed of change of long-term co-debt.

6. A method for determining the debt repayment stability of a credit user as claimed in claim 1, characterized in that: The assessment of the debt pressure trend of the borrower is specifically as follows: By comparing the loan information in two cross-time zone PBOC personal credit information reports, the target user's credit fund outflow and inflow are evaluated; Analyze debt concentration to determine whether the borrower is an active account master or a passive account master.

7. A method for determining the stability of a credit user's debt repayment as claimed in claim 1, characterized in that: The debt repayment stability coefficient is calculated by the following formula: Debt repayment stability coefficient = ∑(basic qualifications * customer base stability * multiple debt degree trend * debt pressure trend).

8. A method for determining the debt repayment stability of a credit user as claimed in claim 1, characterized in that: The rationality and consistency of the debt repayment stability coefficient is verified on the risk sample with a long performance cycle, specifically: Divide the borrower population into multiple gradients based on risk statistical parameter values, each gradient represents a different risk level; Within each gradient, the average or median of the debt repayment stability coefficient is calculated to assess the overall debt repayment stability of borrowers within the gradient; Compare the differences in debt repayment stability coefficients between different gradients to verify whether they are consistent with the gradient change trend of the risk statistical parameters, so as to confirm the consistency of the strength of stability and the gradient of risk statistical parameters among the borrowing groups.

9. A system for determining the stability of a credit user's debt repayment, characterized in that: Includes the following modules: A multi-dimensional information collection module, which is used to collect multi-dimensional information of the borrower, wherein the multi-dimensional information includes at least basic information, credit data and third-party data; A data analysis and processing module, which is used to analyze and process the collected multi-dimensional data, and extract sub-items that can reflect the borrower's qualifications, customer base stability, multiple debt degree trends, and debt pressure trends; A stability prediction variable extraction and model input module, wherein the stability prediction variable extraction and model input module extracts stability prediction variables from the multi-dimensional information after parsing and processing; the extracted stability prediction variables are input into a preset model, and the model is trained and optimized to calculate the debt repayment stability coefficient of the target user based on the input variables; A debt repayment stability coefficient verification module is used to verify the rationality and consistency of the debt repayment stability coefficient on risk samples.

10. A system for determining the stability of a credit user's debt repayment as claimed in claim 9, characterized in that: The system further comprises an output and feedback module, wherein the output and feedback module is used to output the calculated debt repayment stability coefficient and a credit decision suggestion based on the coefficient; Receive feedback from credit operations personnel for continuous optimization and improvement of the system.

Images