Using method of credit loan limit model under multiple conditions

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a method for using a credit loan limit model under multiple conditions, and the method comprises the steps: obtaining historical credit associated data of a client; based on the historical credit associated data, constructing an income and liability model used for predicting liability risks of customers and a credit default model used for predicting default risks of the customers; constructing a limit model based on a credit business demand corresponding to the client, the income and liability model and the credit default model; and performing consumption credit limit prediction on current credit associated data of a new client based on the limit model to obtain a target credit limit of the new client. According to the method, the target credit line of the new client can be more scientifically and accurately predicted through the line model, so that the risk of a financial institution is reduced, and market changes can be more accurately adapted.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method for using a credit loan limit model under multiple conditions in the field of artificial intelligence technology. Background Art

[0002] With the rapid expansion of personal consumer loans, credit limit management and differentiated pricing have become important parts of whether financial institutions can maximize profits. Among them, credit limit strategy will directly affect the risk management, customer satisfaction and profitability of banks or other financial institutions. A reasonable credit limit strategy can help banks control risks. If the credit limit is too high, it may lead to excessive debt of borrowers and increase the risk of default; if the credit limit is too low, it may not meet the actual needs of borrowers and lead to customer loss.

[0003] In related technologies, appropriate adjustments are made based on the user's income level and debt level, combined with the user's customer qualifications, asset status, and risk information. In this way, the cost of manual calculation and adjustment is too high based on manual historical experience decisions, and the risk of financial institutions is relatively high. Summary of the invention

[0004] In order to solve the technical problem of load imbalance caused by multiple clients connecting to the same server in the prior art, the present invention aims to provide a method for using a credit loan limit model under multiple conditions. The technical solution adopted is as follows: In a first aspect, an embodiment of the present invention provides a method for using a credit loan limit model under multiple conditions, the method comprising: Obtain the client's historical credit-related data; Based on the historical credit correlation data, construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk; Constructing a credit line model based on the credit business needs corresponding to the client, the income liability model and the credit default model; Based on the credit limit model, a consumer credit limit prediction is performed on the current credit-related data of the new client to obtain a target credit limit of the new client.

[0005] In a second aspect, a system for using a credit loan limit model under multiple conditions is provided, the system comprising: The acquisition module is used to obtain the client's historical credit-related data; A first construction module is used to construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk based on the historical credit association data; A second construction module is used to construct a credit limit model based on the credit business demand corresponding to the client, the income liability model and the credit default model; The prediction module is used to predict the consumer credit limit of the new client based on the credit limit model, so as to obtain the target credit limit of the new client.

[0006] In a third aspect, a computer program product is provided, which includes: a computer program code, which, when executed on a computer, enables the computer to execute a method for using a credit loan limit model under multiple conditions in any one of the possible implementations described above.

[0007] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes a method for using a credit loan limit model under multiple conditions in any possible implementation described above.

[0008] The present invention has the following beneficial effects: first, the historical credit association data of the client is obtained, and an income-liability model and a credit default model are constructed through the historical credit association data, so as to predict the client's liability risk through the income-liability model, and predict the client's default risk through the credit default model. Afterwards, a credit limit model is constructed through the credit business demand corresponding to the client, combined with the output result of the income-liability model and the output result of the credit default model, so as to predict the consumer credit limit of the client's current credit association data through the credit limit model, and obtain the target credit limit of the new client. In this way, the income-liability model and the credit default model are constructed through the historical credit association data, so that the debt risk and default risk of the client can be accurately predicted; and the credit business demand corresponding to the client, the income-liability model and the credit default model are combined to construct a credit limit model, so that the target credit limit of the new client can be more scientifically and accurately predicted through the credit limit model, so as to reduce the risk of financial institutions and adapt to market changes more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0010] Figure 1 It is a schematic diagram of a flow chart of a method for using a credit loan limit model under multiple conditions provided by an embodiment of the present invention; Figure 2 It is another implementation flow diagram of a method for using a credit loan limit model under multiple conditions provided by an embodiment of the present invention; Figure 3 It is another implementation flow diagram of a method for using a credit loan limit model under multiple conditions provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the composition structure of a system for using a credit loan quota model under multiple conditions provided by an embodiment of the present invention; Figure 5 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for using a credit loan limit model under multiple conditions proposed by the present invention, its specific implementation method, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0012] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more than two.

[0013] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0014] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0015] The present invention provides a specific scheme for using a credit loan limit model under multiple conditions. Figure 1 , which shows a schematic diagram of the implementation process of a method for using a credit loan limit model under multiple conditions provided by an embodiment of the present invention. The method can be implemented by the following steps: 101, obtain the client's historical credit related data.

[0016] Here, the client can be a terminal corresponding to any type of client of a credit institution. The historical credit-related data includes: the client's identity information, historical amount-related data, historical credit records and historical consumption behavior data; among which, the historical amount-related data includes: income-related data and asset-related data.

[0017] In some possible implementations, the identity information, historical amount-related data, historical credit record and historical consumption behavior data of the client are first obtained; for example, multi-dimensional data of the customer is collected, including but not limited to identity information (for example, age, gender, occupation, etc.), income-related data (for example, salary income, bonus income, investment income, etc.), asset-related data (for example, real estate, vehicles, etc.), debt status, credit record (for example, bank credit report, online loan platform record, etc.), consumption behavior data (for example, consumption frequency, consumption amount, consumption category, etc.).

[0018] Then, the identity information, historical amount-related data, historical credit records and historical consumption behavior data are pre-processed to obtain the historical credit-related data.

[0019] For example, data preprocessing and feature processing are performed on identity information, historical amount-related data, historical credit records, and historical consumer behavior data. The quality and availability of the historical credit-related data obtained are ensured by cleaning, denoising, and standardizing the collected data. For example, outliers are removed or missing values ​​are filled in for identity information, historical amount-related data, historical credit records, and historical consumer behavior data. In this way, by preprocessing and feature processing the collected client data, the availability of historical credit-related data can be improved.

[0020] 102. Based on the historical credit correlation data, construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk.

[0021] Here, by reading historical amount-related data from the historical credit-related data and performing feature extraction, an income-liability model can be constructed. In some possible implementations, the "constructing an income-liability model for predicting customer liability risk based on the historical credit-related data" in step 102 can be accomplished by Figure 2 The steps shown achieve: 201, determining historical amount related data in the historical credit related data.

[0022] Here, after obtaining the historical credit-related data, historical amount-related data is called from the historical credit-related data, for example, income-related data is called from the historical credit-related data.

[0023] 202, extracting features from the historical amount-related data to obtain amount data features.

[0024] Here, by extracting features from the income-related data in the historical amount-related data, the client's income stability index and debt ratio characteristics are analyzed to obtain the amount data characteristics.

[0025] In some possible implementations, the above step 202 may be implemented by the following steps 221 to 223 (not shown): 221. Determine the income stability indicator characteristics of the client based on the work status of the client to which the client belongs and the income-related data in the historical amount-related data.

[0026] Here, the working conditions of the clients of the client include: the working years of the clients, the stability of the industry they are in, and the operating conditions of the company. The average income data of the client is determined by the income-related data; for example, the total income of the client in a certain period of time is divided by the length of the period of time to obtain the average income data, and the average income data of the clients of the client is obtained by calculating the mean of the income-related data. After that, the income fluctuation analysis is performed on the income-related data to obtain the analysis results; for example, the standard deviation or variance of the income of the client in different time periods is calculated to measure the degree of income fluctuation. The smaller the fluctuation, the higher the income stability. Finally, based on the working information of the client, the working stability weight of the client is determined; and based on the average income data, the analysis results and the working stability, the income stability index of the client is determined. Here, the corresponding weight is given in combination with factors such as the working years of the client, the stability of the industry they are in, and the operating conditions of the company. For example, the longer the working years, the higher the industry stability, and the better the company's operating conditions, the higher the weight of the working stability. The average income data, the income fluctuation degree and the working stability weight are comprehensively calculated to obtain the income stability index. For example, the weighted average method can be used to give different weights to average income, income volatility, and job stability, and then perform calculations to accurately obtain the client's income stability indicator characteristics.

[0027] 222. Determine the debt ratio characteristics of the client based on the debt-related data in the historical amount-related data.

[0028] Here, based on the debt-related data, the total debt and total assets of the client are analyzed; and based on the total assets and the total debt, the debt ratio feature is determined. In some possible implementations, by collecting the debt-related data of the customer, including but not limited to credit card arrears, mortgages, car loans, other loans, etc. At the same time, obtain the customer's asset information, such as property value, vehicle value, deposits, etc. After that, calculate the total debt, for example, add up all the debt amounts of the customer to get the total debt. And calculate the total assets, for example, add up all the asset values ​​of the customer to get the total assets. In this way, the debt ratio feature = total debt / total assets. Different types of debt (such as credit card arrears, mortgages, car loans, etc.) and debts of different terms have different effects on the repayment pressure of the customer. Different weights can be given according to the type and term of debt to adjust the debt ratio feature. For example, the weight of credit card arrears can be relatively high because its repayment period is short and the interest rate is high; the weight of mortgages can be relatively low because its repayment period is long and the interest rate is relatively stable.

[0029] 223, determining the client's income stability index feature and the debt ratio feature as the amount data feature. In this way, by using the client's income stability index feature and the debt ratio feature as the amount data feature, it is convenient to subsequently evaluate the client's debt situation.

[0030] 203. Obtain the income-liability model based on the amount data feature.

[0031] Here, the average income data of the client is calculated, the income fluctuation analysis is conducted, and the job stability is taken into consideration and given corresponding weights. Finally, the income stability indicator characteristics are obtained through comprehensive calculation. In addition, liability-related data and asset information are collected, the total liabilities and total assets are calculated, the debt ratio characteristics are obtained, and different weights are given for adjustment considering the type and term of liabilities.

[0032] The characteristics of the income stability index and the debt ratio can be divided into different layers, such as high, medium and low. The "income debt model" is derived by combining the two indicators. For example, users with high income stability and low debt ratio will have a high level in the income debt model. In this way, by extracting the amount data characteristics, the income and debt situation of the client can be accurately analyzed.

[0033] In some possible implementations, the step 102 of “building a credit default model for predicting customer default risk based on the historical credit association data” may be implemented by: Figure 3 The steps shown achieve: 301, determining historical default-related data in the historical credit-related data.

[0034] Here, historical default related data are read from the historical credit-related data, such as the user's age and basic information related to occupation; historical credit records and repayment status of banks and online loan platforms; consumption behavior related data, including consumption frequency and consumption amount; and user asset status, including real estate and car ownership.

[0035] 302, extracting features from the historical default related data to obtain default features.

[0036] Here, feature extraction of historical default-related data is performed through machine learning algorithms to obtain default features.

[0037] 303. Construct the credit default model based on the default characteristics.

[0038] Here, the input variables (feature variables) and output variables (credit default status) of the credit default model are determined, where the input variables are the default features of historical default-related data, and the output variables are whether the user's loan is overdue during a specific observation period. A convolutional neural network can be used to build a credit default model; then, the data set (i.e., historical default-related data) is divided into a training set and a test set, and the training set is used to train the model, adjust the model parameters, and improve the model performance. At the same time, the test set is used to evaluate the credit default model to verify the prediction accuracy and generalization ability of the model. In this way, the default features are extracted through historical default-related data, and the network model is trained to obtain a credit default model that can accurately predict the customer's default risk.

[0039] 103. Construct a credit limit model based on the credit business demand corresponding to the client, the income liability model and the credit default model.

[0040] Here, by analyzing the risk assessment threshold of credit business demand, the output results of the income liability model and the credit default model are combined to jointly construct a credit limit model.

[0041] In some possible implementations, first, determine the risk assessment threshold that matches the credit business demand; for example, clarify the risk, profit, balance size, etc. according to the credit business demand for business development; for example, the risk assessment threshold includes constraints such as profit maximization, minimum total credit amount, and maximum balance size. Then, determine the output results of the historical credit association data in the income liability model and the credit default model; here, the output results of the historical credit association data in the income liability model and the credit default model are used as the input of the credit limit model. Finally, construct the credit limit model based on the risk assessment threshold and the output results. Here, the income-liability model, credit default model, constraints and other characteristics (among which, other characteristics include: 1. The customer's historical loan application behavior characteristics, such as the number of applications, the time interval between applications, etc.; 2. The customer's social relationship network characteristics, if relevant data can be obtained, may reflect the customer's credit dissemination and risk association; 3. Macroeconomic environment characteristics, such as the current economic situation, industry development trends, etc., these factors may affect the customer's repayment ability and default risk, and thus affect the credit limit decision.) are used as input, and the consumer credit limit is used as output. The automatic machine learning (autoML) algorithm is used to fit the logical relationship between risk and limit, profit and balance, so as to automatically output the optimal limit and realize the training of the limit model; thus, the trained limit model can accurately predict the customer's target credit limit based on the client's current credit-related data.

[0042] 104. Based on the credit limit model, predict the consumer credit limit of the new client's current credit-related data to obtain a target credit limit of the new client.

[0043] Here, the current credit-related data of the new client is input into the trained credit limit model to obtain the estimated result of the consumer credit limit, i.e., the target credit limit. At the same time, the repayment status and credit status changes of the new client are obtained; for example, the repayment performance, credit status changes and other real-time data of the new client. Afterwards, based on the repayment status and credit status changes, the target credit limit of the new client is updated. Here, the credit limit is dynamically adjusted according to the real-time data such as the repayment performance and credit status changes of the client, so that the updated target credit limit can better match the current economic status of the new customer and reduce the risk of the financial institution.

[0044] In an embodiment of the present invention, after obtaining the historical credit-related data of the client, the client's liability risk is predicted through the income-liability model, and the client's default risk is predicted through the credit default model. A credit limit model is constructed by combining the output results of the income-liability model and the output results of the credit default model according to the client's corresponding credit business needs, so that the consumer credit limit of the client's current credit-related data can be predicted through the credit limit model to obtain the client's target credit limit. In this way, the income-liability model and the credit default model are constructed through historical credit-related data, so that the client's liability risk and default risk can be accurately predicted; and the credit business needs corresponding to the client, the income-liability model and the credit default model are combined to construct a credit limit model, so that the target credit limit of the new client can be more scientifically and accurately predicted through the credit limit model, so as to reduce the risk of financial institutions and adapt to market changes more accurately.

[0045] The embodiment of the present invention provides a system for using a credit loan limit model under multiple conditions, such as Figure 4 As shown, the system 400 includes: Acquisition module 401, used to acquire historical credit-related data of the client; A first construction module 402 is used to construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk based on the historical credit association data; The second construction module 403 is used to construct a credit limit model based on the credit business demand corresponding to the client, the income liability model and the credit default model; The prediction module 404 is used to predict the consumer credit limit of the new client based on the credit limit model, and obtain the target credit limit of the new client.

[0046] In some possible implementations, the acquisition module 401 is also used to obtain the identity information, historical amount-related data, historical credit records, and historical consumption behavior data of the client; and perform data preprocessing on the identity information, historical amount-related data, historical credit records, and historical consumption behavior data to obtain the historical credit-related data.

[0047] In some possible implementations, the first construction module 402 is further used to determine historical amount-related data in the historical credit-related data; perform feature extraction on the historical amount-related data to obtain amount data features; and obtain the income-liability model based on the amount data features.

[0048] In some possible implementations, the first construction module 402 is further used to determine the income stability index characteristics of the client based on the work status of the customer to which the client belongs and the income-related data in the historical amount-related data; determine the debt ratio characteristics of the client based on the debt-related data in the historical amount-related data; and determine the income stability index characteristics and the debt ratio characteristics of the client as the amount data characteristics.

[0049] In some possible implementations, the first construction module 402 is further used to determine the average income data of the clients of the client based on the income-related data; perform income fluctuation analysis on the income-related data to obtain analysis results; determine the job stability weight of the client based on the work situation of the client; and determine the income stability index of the client based on the average income data, the analysis results and the job stability.

[0050] In some possible implementations, the first construction module 402 is further configured to determine total liabilities and total assets based on the liabilities-related data; and determine the liabilities ratio characteristics based on the total assets and the total liabilities.

[0051] In some possible implementations, the first construction module 402 is further used to determine historical default-related data in the historical credit-related data; perform feature extraction on the historical default-related data to obtain default features; and construct the credit default model based on the default features.

[0052] In some possible implementations, the second construction module 403 is further used to determine a risk assessment threshold for matching the credit business demand; determine output results of the historical credit correlation data in the income liability model and the credit default model; and construct the credit limit model based on the risk assessment threshold and the output results.

[0053] In some possible implementations, the prediction module 404 is further used to obtain the repayment status and credit status changes of the new client; and update the target credit limit of the new client based on the repayment status and the credit status changes.

[0054] Optionally, the transmission medium can be a wired link (such as but not limited to coaxial cable, optical fiber and digital subscriber line (DSL), etc.) or a wireless link (such as but not limited to wireless Fidelity (WIFI), Bluetooth and mobile device network, etc.). It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the method embodiments provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0055] Figure 5 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 5 As shown, the computer device 500 includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any one of the methods for using the credit loan limit model under multiple conditions introduced above.

[0056] In addition, an embodiment of the present invention also protects a system, which may include a memory and a processor, wherein an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to perform a method for using a credit loan limit model under multiple conditions provided by an embodiment of the present invention. This embodiment can divide the system into functional modules according to the above method example. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic, which is only a logical function division. There may be other division methods in actual implementation. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0057] It should be understood that the system provided in this embodiment is used to execute the above-mentioned method of using a credit loan limit model under multiple conditions, so the same effect as the above-mentioned implementation method can be achieved. In the case of an integrated unit, the system may include a processing module and a storage module. Among them, when the system is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic boxes, modules and circuits described in conjunction with the disclosure of the present invention. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module can be a memory.

[0058] In addition, the system provided by the embodiment of the present invention may be specifically a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip may execute a method for using a credit loan limit model under multiple conditions provided by the above embodiment. This embodiment also provides a computer-readable storage medium, in which a computer program code is stored, and when the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement a method for using a credit loan limit model under multiple conditions provided by the above embodiment.

[0059] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer executes the above-mentioned related steps to implement a method for using a credit loan quota model under multiple conditions provided by the above embodiment. Among them, the system, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here. Through the description of the above implementation mode, the technicians in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional modules as needed, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, system or unit, which may be electrical, mechanical or other forms.

[0060] It should be noted that the sequence of the above-mentioned embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous. The various embodiments in this specification are described in a progressive manner, and the same and similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments. The above content is only a specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention.

Claims

1. A method for using a credit loan limit model under multiple conditions, characterized in that: The method comprises: Obtain the client's historical credit-related data; Based on the historical credit correlation data, construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk; Constructing a credit line model based on the credit business needs corresponding to the client, the income liability model and the credit default model; Based on the credit limit model, a consumer credit limit prediction is performed on the current credit-related data of the new client to obtain a target credit limit of the new client.

2. The method for using the credit loan limit model under multiple conditions according to claim 1, characterized in that: The obtaining of the client's historical credit-related data includes: Obtain the client's identity information, historical amount-related data, historical credit records, and historical consumption behavior data; The identity information, historical amount-related data, historical credit records and historical consumption behavior data are pre-processed to obtain the historical credit-related data.

3. The method for using the credit loan limit model under multiple conditions according to claim 1, characterized in that: Based on the historical credit correlation data, an income-liability model for predicting customer liability risk is constructed, including: Determining historical amount-related data in the historical credit-related data; Extracting features from the historical amount-related data to obtain amount data features; Based on the amount data characteristics, the income liability model is obtained.

4. The method for using a credit loan limit model under multiple conditions according to claim 3, characterized in that: The feature extraction of the historical amount-related data to obtain amount data features includes: Determine the income stability indicator characteristics of the client based on the work status of the client to which the client belongs and the income-related data in the historical amount-related data; Determining the debt ratio characteristics of the client based on the debt-related data in the historical amount-related data; The income stability index feature and the debt ratio feature of the client are determined as the amount data feature.

5. The method for using the credit loan limit model under multiple conditions according to claim 4, characterized in that: The determining of the income stability indicator characteristics of the client based on the work status of the client to which the client belongs and the income-related data in the historical amount-related data includes: Based on the income-related data, determine average income data of customers to which the client belongs; Performing income fluctuation analysis on the income-related data to obtain analysis results; Determining a job stability weight of the client based on the client's job situation; Based on the average income data, the analysis results and the job stability, an income stability index of the client is determined.

6. A method for using a credit loan limit model under multiple conditions according to claim 4, characterized in that: The determining of the debt ratio characteristics of the client based on the debt-related data in the historical amount-related data includes: Determine total liabilities and total assets based on the liability-related data; The debt ratio characteristic is determined based on the total assets and the total liabilities.

7. The method for using a credit loan limit model under multiple conditions according to claim 1, characterized in that: Based on the historical credit association data, a credit default model for predicting customer default risk is constructed, including: Determining historical default-related data from the historical credit-related data; Extracting features from the historical default-related data to obtain default features; Based on the default characteristics, the credit default model is constructed.

8. The method for using a credit loan limit model under multiple conditions according to claim 1, characterized in that: The constructing of a credit line model based on the credit business demand corresponding to the client, the income liability model and the credit default model includes: Determine the risk assessment threshold matching the credit business demand; Determine the output results of the historical credit association data in the income liability model and the credit default model; The credit limit model is constructed based on the risk assessment threshold and the output result.

9. The method for using a credit loan limit model under multiple conditions according to claim 1, characterized in that: The method further comprises: Obtaining the repayment status and credit status changes of the new client; Based on the repayment status and the change in credit status, the target credit limit of the new client is updated.

10. A system for using a credit loan limit model under multiple conditions, characterized in that: The system comprises: The acquisition module is used to obtain the historical credit-related data of the client; A first construction module is used to construct an income liability model for predicting customer liability risk and a credit default model for predicting customer default risk based on the historical credit association data; A second construction module is used to construct a credit limit model based on the credit business demand corresponding to the client, the income liability model and the credit default model; The prediction module is used to predict the consumer credit limit of the new client based on the credit limit model, so as to obtain the target credit limit of the new client.

Images