CN110610412A

CN110610412A - Credit risk assessment method and device, storage medium and electronic equipment

Info

Publication number: CN110610412A
Application number: CN201910824927.XA
Authority: CN
Inventors: 周立勇; 罗广锋; 曾丹萍; 李来; 孙自朋; 李珊珊
Original assignee: Shenzhen Zhong Xing Credex Finance Tecnnology Ltd
Current assignee: Shenzhen Zhong Xing Credex Finance Tecnnology Ltd
Priority date: 2019-09-02
Filing date: 2019-09-02
Publication date: 2019-12-24

Abstract

The present disclosure relates to a credit risk assessment method and apparatus, a storage medium, and an electronic device to solve a problem that it is difficult to accurately assess a user's credit risk. The method comprises the following steps: acquiring characteristic information of a target user; and inputting the characteristic information into a pre-established risk assessment model, and outputting a credit risk assessment result of the target user, wherein the risk assessment model is obtained by training the characteristic information of different users and the credit risk assessment result thereof as training samples. The method and the device can accurately evaluate the credit risk of the user through a pre-established risk evaluation model.

Description

Credit risk assessment method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of information technology, and in particular, to a credit risk assessment method and apparatus, a storage medium, and an electronic device.

Background

Credit lending refers to a new consumption method of providing a borrowed product according to the credit of a user, and the user can obtain the product by the credit of the user without providing collateral or third party guarantee, and the credit degree of the user is used as the guarantee of payment.

In the business field of credit loan and the like, credit risk assessment is generally required for users. In the related art, credit risk assessment is usually performed on a user according to credit investigation information of the user, however, some users transact credit cards to banks, but use few credit cards and have only a small amount of credit card information, or do not apply credit cards to banks, have no credit card information, never transact any network loan, and have no loan relation with financial institutions, so the credit investigation information of the some users is weak and even has no credit investigation information, and therefore, the method is difficult to accurately assess the credit risk of the user.

Disclosure of Invention

The purpose of the present disclosure is to provide a credit risk assessment method and apparatus, a storage medium, and an electronic device, so as to solve the problem in the related art that it is difficult to accurately assess the credit risk of a user.

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, the present disclosure provides a credit risk assessment method, the method comprising: acquiring characteristic information of a target user; and inputting the characteristic information into a pre-established risk assessment model, and outputting a credit risk assessment result of the target user, wherein the risk assessment model is obtained by training the characteristic information of different users and the credit risk assessment result thereof as training samples.

Optionally, the risk assessment models are multiple, and each risk assessment model corresponds to a user category, wherein the user categories are obtained by dividing according to historical credit investigation information of users; wherein each risk assessment model is established according to the following ways: acquiring historical characteristic information of a plurality of users belonging to the same user category; aiming at each user, determining a credit risk evaluation result of the user according to the historical characteristic information of the user and a preset credit risk evaluation rule corresponding to the user category; training a logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk assessment result corresponding to the historical characteristic information as training samples to obtain a risk assessment model corresponding to the user category; the inputting of the characteristic information into a pre-established risk assessment model comprises: determining the user category to which the target user belongs according to the characteristic information of the target user; and inputting the characteristic information of the target user into a risk assessment model corresponding to the user category.

Optionally, before the inputting the feature information into a pre-established risk assessment model, the method further includes: judging whether the target user accords with a preset admission rule or not; the inputting of the characteristic information into a pre-established risk assessment model comprises: and if the target user is determined to accord with the access rule, inputting the characteristic information into the risk assessment model.

Optionally, the method further comprises: determining credit limit information of the target user at least according to a credit risk evaluation result of the target user; and determining credit product information pushed for the target user according to the credit line information.

Optionally, the determining the credit line information of the target user according to at least the credit risk assessment result of the target user includes: determining the default probability grade of the target user according to the credit risk evaluation result of the target user; and outputting the credit line information of the target user according to the default probability level of the target user and the preset corresponding relation between the default probability level and the credit line information.

Optionally, the determining the credit line information of the target user according to at least the credit risk assessment result of the target user includes: obtaining repayment capability characteristic information of the target user according to the characteristic information of the target user; obtaining the repayment capacity grade of the target user according to the repayment capacity characteristic information; and obtaining the credit line information of the target user according to the repayment ability level of the target user and the preset corresponding relation among the default probability level, the repayment ability level and the credit line information.

In a second aspect, the present disclosure provides a credit risk assessment apparatus, the apparatus comprising: the information acquisition module is used for acquiring the characteristic information of the target user; and the risk evaluation module is used for inputting the characteristic information into a pre-established risk evaluation model and outputting a credit risk evaluation result of the target user, wherein the risk evaluation model is obtained by training the characteristic information of different users and the credit risk evaluation result thereof as training samples.

Optionally, the risk assessment module comprises: the acquisition submodule is used for acquiring historical characteristic information of a plurality of users belonging to the same user category; the determining submodule is used for determining a credit risk evaluation result of each user according to the historical characteristic information of the user and a preset credit risk evaluation rule corresponding to the user category; and the risk evaluation submodule is used for training the logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk evaluation result corresponding to the historical characteristic information as training samples to obtain a risk evaluation model corresponding to the user category.

The determining submodule is further configured to determine, according to the feature information of the target user, a user category to which the target user belongs; and inputting the characteristic information of the target user into a risk assessment model corresponding to the user category.

Optionally, the apparatus further comprises: the judging module is used for judging whether the target user accords with a preset admission rule or not; the risk assessment model is further configured to input the feature information into the risk assessment model when it is determined that the target user complies with the admission rule.

Optionally, the apparatus further comprises: the result determining module is used for determining the credit line information of the target user at least according to the credit risk evaluation result of the target user; and the credit module is used for determining the credit product information pushed for the target user according to the credit limit information.

Optionally, the result determination module includes: the first result determining submodule is used for determining the default probability level of the target user according to the credit risk evaluation result of the target user; the second result determining submodule is used for outputting the credit line information of the target user according to the default probability level of the target user and the preset corresponding relation between the default probability level and the credit line information;

the result determination module includes: the third result determining submodule is used for obtaining the repayment capability characteristic information of the target user according to the characteristic information of the target user; a fourth result determining submodule, configured to obtain a repayment capability level of the target user according to the repayment capability feature information; and the fifth result determining submodule is used for obtaining the credit line information of the target user according to the repayment ability level of the target user and the preset corresponding relation among the default probability level, the repayment ability level and the credit line information.

In a third aspect, the present disclosure provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the credit risk assessment methods.

In a fourth aspect, the present disclosure provides an electronic device comprising: a memory having a computer program stored thereon; a processor for executing the computer program in the memory to implement the steps of any of the credit risk assessment methods.

The technical scheme can at least achieve the following technical effects:

by acquiring the characteristic information of the target user and inputting the characteristic information into the pre-established risk assessment model, the risk assessment model is obtained by training the historical characteristic information of different users and credit risk assessment results of the different users as training samples, and the credit risk assessment result of the target user is further output, so that the credit risk of the user can be accurately assessed through the pre-established risk assessment model according to the characteristic information of the target user, and the accuracy of assessing the credit risk of the user is improved.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:

FIG. 1 is a flow chart illustrating a credit risk assessment method according to an exemplary disclosed embodiment.

FIG. 2 is a flow chart illustrating a method of credit risk assessment according to an exemplary disclosed embodiment.

FIG. 3 is a flow chart illustrating a method of credit risk assessment according to an exemplary disclosed embodiment.

FIG. 4 is a flow chart illustrating another credit risk assessment method according to an exemplary disclosed embodiment.

FIG. 5 is a block diagram illustrating a credit risk assessment device according to an exemplary embodiment.

FIG. 6 is a block diagram of an electronic device shown in accordance with an example embodiment.

FIG. 7 is a block diagram of another electronic device shown in accordance with an example embodiment.

Detailed Description

The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.

FIG. 1 is a flow chart illustrating a method of information evaluation according to an exemplary disclosed embodiment.

And S11, acquiring the characteristic information of the target user.

In particular implementations, the characteristic information may include age information, professional information, income information, credit card transaction and usage information, credit investigation information, and the like of the target user.

Optionally, the characteristic information may be obtained based on the application information of the target user, may also be obtained based on an internal database, and may also be obtained based on a data information base of a third party platform, where the data information base of the third party platform refers to data information of the target user introduced by the third party platform, for example, a credit investigation system data information base of a chinese people bank.

In an alternative embodiment, first, the name, age, identification card information, income information, and occupation information of the target user are obtained based on the application information of the target user. Secondly, based on the application information, the historical characteristic information of the target user, such as whether the credit card is transacted, the use frequency of the credit card and the historical payment information of the credit card, is matched from an internal database. And thirdly, introducing third-party platform data information, such as credit investigation system data information of China people's bank, based on the application information and/or the historical characteristic information of the target user matched with the internal database to acquire the historical credit investigation information of the target user.

And S12, inputting the characteristic information into a pre-established risk assessment model, and outputting a credit risk assessment result of the target user.

The risk assessment model is obtained by training the characteristic information of different users and credit risk assessment results of the characteristic information as training samples.

The risk assessment models are multiple, each risk assessment model corresponds to a user category, and the user categories are obtained by dividing according to historical credit investigation information of users.

Each risk assessment model is built according to the following modes:

acquiring historical characteristic information of a plurality of users belonging to the same user category;

aiming at each user, determining a credit risk evaluation result of the user according to the historical characteristic information of the user and a preset credit risk evaluation rule corresponding to the user category;

and training the logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk assessment result corresponding to the historical characteristic information as training samples to obtain the risk assessment model corresponding to the user category.

It should be noted that the credit risk assessment result may be a credit risk assessment score to obtain credit risk assessment results with different scores, and further obtain a logistic regression model with different scores. Or credit risk assessment grades, and obtaining credit risk assessment results of different grades. Further, logistic regression models of different grades are obtained.

Illustratively, first, historical characteristic information of a plurality of users, such as credit debit and credit information and historical credit card transaction and use information, is acquired, and the users are classified into three types of clients with little credit card information, no credit card information and no credit debit and credit information according to the historical characteristic information.

Secondly, for each user, according to the historical characteristic information of the user and a preset credit risk assessment rule corresponding to the user category, determining a credit risk assessment result of the user, such as whether the user pays according to time or full amount, whether the user pays according to the time or the full amount, and whether the user pays according to the time or the full amount, or pays according to the time or the full amount more than half times. And determining a credit risk evaluation result of the user according to the historical characteristic information of each user and a preset credit risk evaluation rule thereof. For example, if a small amount of credit card information exists, corresponding to full payment at each time, the credit risk assessment result of the user is determined to be good; if a small amount of credit card information exists, corresponding to the events of payment delay or insufficient money and the like, determining the credit risk evaluation result of the user as middle; if a small amount of credit card information exists and more than half times of repayment time is delayed or the amount of money is insufficient, determining that the credit risk evaluation result of the user is poor; if no credit card information exists, but debit and credit information of other platforms exists, and the full payment is carried out every time, the credit risk evaluation result of the user is determined to be good; if no credit card information exists, but debit and credit information of other platforms exists, and if the repayment time is delayed or the amount of money is insufficient, the credit risk assessment result of the user is determined to be middle; if no credit card information exists, but debit and credit information of other platforms exists, and the credit risk assessment result of the user is determined to be poor if more than half of repayment time is delayed or the amount of money is insufficient; and if no credit borrowing and lending information exists and no repayment information exists, determining that the credit risk evaluation result of the user is medium.

And finally, training the logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk assessment result corresponding to the historical characteristic information as training samples to obtain a risk assessment model corresponding to the user category. For example, if the credit risk assessment result of the user is good, the user is used as a training sample to train the logistic regression model, and then the logistic regression model with the good class is obtained; taking the credit risk assessment result of the user as a middle, training the logistic regression model as a training sample, and obtaining the logistic regression model with the middle class; and (4) the credit risk evaluation result of the user is poor, and the user is used as a training sample to train the logistic regression model, so that the logistic regression model with the category of poor grade is obtained.

In a possible implementation manner, the risk assessment models are different types of score risk assessment models, and if a good risk assessment result score is 5, the logistic regression model score is 5; if the credit risk assessment score of the medium assessment result in the risk assessment result is 10 points, the score of the obtained logistic regression model is 10 points; and if the credit risk assessment score of the poor risk assessment result and the poor assessment result is 15 points, the score of the obtained logistic regression model is 15 points. Wherein a higher score for the risk assessment result indicates a higher risk for the credit risk assessment.

In another possible implementation manner, the risk assessment models are different types of grade risk assessment models, and if the grade of a good risk assessment result is low, the grade of the obtained logistic regression model is low; if the risk evaluation result grade is middle, the logistic regression model grade is obtained; and if the poor risk assessment result is high, the credit risk assessment grade of the logistic regression model with the high and good assessment results is low, the credit risk assessment grade of the medium assessment result is medium, and the credit risk assessment grade of the poor assessment result is high.

The inputting of the characteristic information into a pre-established risk assessment model comprises:

determining the user category to which the target user belongs according to the characteristic information of the target user;

and inputting the characteristic information of the target user into a risk assessment model corresponding to the user category.

Illustratively, the user type of the target user is determined based on characteristic information of the target user, such as credit card transaction and usage information, credit solicitation information. And inputting the characteristic information of the target user into a risk assessment model corresponding to the user category, and outputting a credit risk assessment result of the target user.

Optionally, if the risk assessment model outputs different assessment scores, outputting a credit risk assessment score of the target user; and if the risk assessment model outputs different assessment levels, outputting the credit risk assessment level of the target user.

Illustratively, if the characteristic information of the target user is a small amount of credit card information, corresponding to full payment at each time, the characteristic information of the target user is input into a pre-established risk assessment model. If the pre-established logistic regression model is the score model, inputting the logistic regression model with the score of 5 to obtain the credit risk assessment score of 5 of the target user; and if the pre-established logistic regression model is a grade model, inputting the logistic regression model with low grade to obtain that the credit risk evaluation grade of the target user is low.

Illustratively, if the characteristic information of the target user is credit card-free information but debit and credit information of other platforms exists, and the repayment time is delayed by more than half of times or the amount of money is insufficient, the characteristic information of the target user is input into a pre-established risk assessment model. If the pre-established logistic regression model is the score model, inputting the logistic regression model with the score of 15 to obtain the credit risk assessment score of 15 for the target user; and if the pre-established logistic regression model is a grade model, inputting the logistic regression model with high grade to obtain that the credit risk evaluation grade of the target user is high.

Illustratively, if the characteristic information of the target user is no credit loan information, inputting the characteristic information of the target user into a pre-established risk assessment model. If the pre-established logistic regression model is the score model, inputting the logistic regression model with the score of 10 to obtain the credit risk assessment score of 10 of the target user; and if the pre-established logistic regression model is a grade model, inputting the logistic regression model with a medium grade to obtain a credit risk evaluation grade of the target user.

The technical scheme can at least achieve the following technical effects:

FIG. 2 is a flow chart illustrating a method of information evaluation according to an exemplary disclosed embodiment.

And S21, acquiring the characteristic information of the target user.

In a specific implementation, the feature information may include age information, professional information, income information, credit card transaction and use information, credit investigation information, family member information, and the like of the target user.

And S22, judging whether the target user meets the preset admission rule.

For example, the determining whether the target user meets the preset admission rule may be determining whether the age of the target user is within a preset admission age interval.

It is to be understood that the preset admission rule may further include other information, and the preset admission rule may be an admission rule formed by one or more pieces of information.

And S23, if the target user is determined to accord with the admission rule, inputting the characteristic information into the risk assessment model.

For example, the determining whether the target user meets the preset admission rule may be determining whether the age of the target user is within a preset admission age interval. For example, according to the age information in the feature information, whether the age information is in a preset admissible age interval is judged; and if the age information is in a preset access age interval, determining that the target user accords with the access rule, and further inputting the characteristic information into the risk assessment model. For example, the preset admission age interval is 18 years to 50 years, if the age of the target user is 27 years, the age information of the target user is determined to be in the preset injection age interval, further, the target user is determined to meet the admission rule, and further, the characteristic information is input into the risk assessment model.

Optionally, the determining whether the target user meets the preset admission rule may be an admission rule formed by one or more pieces of information.

And S24, outputting the credit risk assessment result of the target user.

And inputting the characteristic information of the target user into a pre-established risk assessment model, and outputting a credit risk assessment result of the target user. For example, the feature information of the target user is input into a pre-established logistic regression model, and the credit risk assessment result of the target user is output.

The technical scheme can at least achieve the following technical effects:

by acquiring the characteristic information of a target user, judging whether the characteristic information of the target user accords with a preset admission rule or not, inputting the characteristic information into a pre-established risk assessment model if the characteristic information accords with the preset admission rule, wherein the risk assessment model is obtained by training historical characteristic information of different users and credit risk assessment results of the historical characteristic information as training samples, and further outputting the credit risk assessment result of the target user.

FIG. 3 is a flow chart illustrating a method of information evaluation according to an exemplary disclosed embodiment.

And S31, acquiring the characteristic information of the target user.

And S32, judging whether the target user meets the preset admission rule.

And S33, if the target user is determined to accord with the admission rule, inputting the characteristic information into the risk assessment model.

And S34, outputting the credit risk assessment result of the target user.

S35, determining the default probability grade of the target user according to the credit risk evaluation result of the target user.

Optionally, if the credit risk assessment result of the target user is an assessment score, determining a default probability score of the target user; and if the credit risk evaluation result of the target user is an evaluation grade, determining the default probability grade of the target user.

Illustratively, if the credit risk assessment result of the target user is an assessment level, determining the default probability level of the target user. If the target user credit risk evaluation grade is low, determining that the default probability grade of the target user is low, if the target user credit risk evaluation grade is medium, determining that the default probability grade of the target user is medium, and if the target user credit risk evaluation grade is high, determining that the default probability grade of the target user is high. Wherein, the default probability level is low to indicate that the default probability is small, and the default probability level is high to indicate that the default probability is large.

S36, outputting the credit line information of the target user according to the default probability level of the target user and the preset corresponding relation between the default probability level and the credit line information.

In one possible implementation manner, if the credit risk assessment result of the target user is an assessment level, determining the default probability level of the target user. Further, according to the preset corresponding relation between the default probability level and the credit line information, the credit line level of the target user is determined.

Exemplarily, if the credit risk evaluation level of the target user is low, determining that the default probability level of the target user is low, and further, determining that the credit line level of the target user is high according to a preset corresponding relation between the default probability level and the credit line information; if the target user credit risk evaluation level is middle, determining that the default probability level of the target user is middle, and further determining the credit line level of the target user according to the preset corresponding relation between the default probability level and the credit line information; and if the credit risk evaluation level of the target user is high, determining that the default probability level of the target user is high, and further determining that the credit line level of the target user is low according to the preset corresponding relation between the default probability level and the credit line information.

And S37, determining the credit product information pushed for the target user according to the credit limit information.

And determining the credit risk of the target user according to the credit risk assessment result assessment score or assessment grade of the target user, and further determining credit product information corresponding to the credit risk.

For example, if the credit risk assessment result of the output target user is low, the credit risk of the target user is determined to be small, and further, a credit product with a higher price and/or a longer repayment period may be pushed to the target user. For example, if the credit risk assessment result of the output target user is 5 or low, a credit product with a price of 10 ten thousand and a repayment period of 12 months is pushed to the target user.

For example, if the output result of the credit risk assessment of the target user is medium, the credit risk of the target user is determined to be medium, and further, a credit product with a slightly lower price and/or a slightly shorter repayment period may be pushed to the target user. For example, if the output credit risk assessment result of the target user is 10 or less, a credit product with a price of 3 ten thousand and a repayment period of 6 months is pushed to the target user.

For example, if the output credit risk assessment result of the target user is high, the credit risk of the target user is determined to be large, and further, a credit product with a low price and/or a short repayment period may be pushed to the target user. For example, if the credit risk assessment result of the output target user is 15 or higher, a credit product with a price of 1 ten thousand and a repayment period of 3 months is pushed to the target user.

Therefore, according to the credit risk evaluation result of the target user, the smaller the credit risk is, the higher the price of the pushed credit product is, the larger the amount of money paid each time is, and the longer the period is; the greater the credit risk, the lower the price of the credit product being pushed, the smaller the amount of money on each repayment, and the shorter the period.

The technical scheme can at least achieve the following technical effects:

In addition, the credit line information of the target user is determined according to the credit risk evaluation result of the target user, and the credit product information pushed for the target user is determined, so that the accuracy of the credit product information pushed for the target user can be improved, and the risk of credit loan is reduced.

FIG. 4 is a flow chart illustrating another method of information evaluation according to an exemplary disclosed embodiment.

S401, obtaining characteristic information of the target user.

S402, judging whether the target user accords with a preset admission rule.

S403, if the target user is determined to accord with the admission rule, inputting the characteristic information into the risk assessment model.

For example, the determining whether the target user meets the preset admission rule may be determining whether the age of the target user is within a preset admission age interval. For example, the determining whether the target user meets the preset admission rule may be an admission rule formed by one or more pieces of information. For example, according to the monthly income information in the feature information, whether the monthly income information is above a preset admission threshold value is judged, and according to the academic information in the feature information, whether the academic information is above a preset admission academic calendar is judged. And if the monthly income information is above a preset admission threshold value and the academic record information is above a preset admission academic record, determining that the target user accords with the admission rule, and further inputting the characteristic information into the risk assessment model.

The risk assessment model is obtained by training the characteristic information of different users and credit risk assessment results of the different users as training samples.

And S404, outputting a credit risk evaluation result of the target user.

For example, if the risk assessment model outputs different assessment scores, the credit risk assessment score of a good assessment result is 5 scores, the credit risk assessment score of a medium assessment result is 10 scores, and the credit risk assessment score of a bad assessment result is 15 scores. Wherein a larger score indicates a greater risk.

For example, if the risk assessment model outputs different assessment levels, the credit risk assessment level of the good assessment result is low, the credit risk assessment level of the medium assessment result is medium, and the credit risk assessment level of the poor assessment result is high.

S405, determining the default probability grade of the target user according to the credit risk evaluation result of the target user.

S406, if the target user is determined to accord with the admission rule, obtaining repayment capability feature information of the target user according to the feature information of the target user.

Optionally, the repayment capability characteristic information of the target user may be a payroll income level of the target user, professional information, whether to purchase a vehicle and a price of purchasing the vehicle, whether to purchase a house, a city where the purchased house is located, a place where the purchased house is located, and the like.

And S407, obtaining the repayment capacity grade of the target user according to the repayment capacity characteristic information.

It can be understood that, in order to improve the accuracy of the repayment ability level of the user, the repayment ability level of the user is determined by a plurality of items of the repayment ability characteristic information, and the more the number of the items of the repayment ability characteristic information is, the more accurate the repayment ability level of the user is.

Illustratively, if a target user A earns 5 thousands of money per month, purchases a vehicle, has a vehicle price of 20 thousands, purchases a house, and the house is located in a sunny area in Beijing, the repayment capability level of the target user A is A; if the target user B earns 5 thousands of money, purchases vehicles, has a price of 20 thousands of money, purchases a house, and the house is located in a mountain area of Beijing City, the repayment capability level of the target user B is B. Wherein the repayment capability level A represents a higher repayment capability than the repayment capability level B represents. This example illustrates that the repayment capability level is affected by the location where the housing was purchased.

For example, if the target user earns 5 thousands of third month, purchases a vehicle, the price of the vehicle is 10 thousands, purchases a house, and the house is located in a mountain area of beijing city, the repayment capacity level of the target user third is C. Wherein the repayment capability level B represents a higher repayment capability than the repayment capability level C represents. This example serves to illustrate that the repayment capability level is affected by the price of the vehicle purchased.

Illustratively, if the target user proceeds 5 thousands of money per month, does not purchase a vehicle, purchases a house, and the house is located in a mountain area of beijing city, the repayment capacity level of the target user is D. Wherein the repayment capability level C represents a higher repayment capability than the repayment capability level D represents. This example illustrates that the repayment capability level is affected by whether or not a vehicle is purchased.

For example, if the target user earns 5 ten thousand in a month without purchasing a vehicle and does not purchase a house, the repayment capacity level of the target user is E. Wherein the repayment capability level D represents a higher repayment capability than the repayment capability level E. This example illustrates that the repayment capability level is affected by whether or not to purchase housing.

For example, if the target user receives 2 million lost, does not purchase a vehicle, and does not purchase a house, the repayment capacity level of the target user is F. Wherein the repayment capability level E represents a higher repayment capability than the repayment capability level F represents. This example serves to illustrate that the repayment capability level is affected by revenue level.

Illustratively, if a target user receives a monthly income of 2 ten thousand, does not purchase a vehicle, does not purchase a house, the target user receives a businessman employee, and the repayment capacity level of the target user is F. If the target user income of the third month is 5 thousands, the vehicle is not purchased, the house is not purchased, the target user third is a bottomless salary salesman, and the repayment capability level of the target user third is F. This example serves to illustrate that the repayment ability level is affected by occupational stability.

It should be noted that the method does not limit the sequence of the step S403 and the step S406. The corresponding steps are performed independently of each other.

S408, obtaining the credit line information of the target user according to the repayment ability level of the target user and the preset corresponding relation among the default probability level, the repayment ability level and the credit line information.

Taking the above examples as examples, the default probability level is low, medium, and high. The repayment capacity levels are A, B, C, D, E and F, wherein the repayment capacity represented by the levels A to F is from high to low, and the preset relationship between the default probability level and the repayment capacity level can be shown in the following table.

And outputting the credit line information of the target user according to the combined relation of the default probability level and the repayment capacity level, wherein a represents that the credit line of the user is the highest, the lower the credit risk of the user is, the gradually lower the credit lines from a to h, the gradually higher the credit risk is, and h represents that the credit line of the user is the lowest, and the higher the credit risk of the user is.

Illustratively, if the characteristic information of the target user is a small amount of credit card information, corresponding to each time, a full payment, a income of 5 thousands, a vehicle purchase, a vehicle price of 20 thousands, a housing purchase, and a housing located in the sunny area in beijing city, it is determined that the default probability level of the target user is low, the payment capability level is a, and further, the credit line information of the target user is output as a.

Illustratively, if the characteristic information of the target user is credit card-free information, but loan information of other platforms exists, corresponding to more than half of times of payment delay or insufficient amount, 5 thousands of monthly income, no vehicle purchase and no house purchase, the default probability level of the target user is determined to be high, the payment capability level is determined to be E, and further, the credit line information of the target user is output to be g.

Illustratively, if the characteristic information of the target user is no credit loan information, 5 thousands of monthly income, vehicle purchase, 10 thousands of vehicle price, housing purchase, and housing location in mountain areas of beijing city, the default probability level of the target user is determined to be middle, the repayment capacity level is determined to be C, and further, the credit line information of the target user is output to be d.

And S409, determining credit product information pushed for the target user according to the credit limit information.

And determining credit product information corresponding to the credit risk according to the credit limit information of the target user. The higher the credit line of the target user is, the credit product with higher price and/or longer repayment period can be pushed to the target user; the lower the credit line of the target user, the lower the price and/or shorter repayment period of the credit product may be pushed to the target user.

For example, if the credit limit information of the target user is a, a credit product with a price of 10 ten thousand and a repayment period of 12 months can be pushed to the target user; if the credit limit information of the target user is b, a credit product with the price of 9 ten thousand and the repayment period of 12 months can be pushed to the target user; if the credit limit information of the target user is c, a credit product with the price of 8 ten thousand and the repayment period of 12 months can be pushed to the target user; if the credit limit information of the target user is d, a credit product with the price of 7 ten thousand and the repayment period of 12 months can be pushed to the target user; if the credit limit information of the target user is e, a credit product with the price of 6 ten thousand and the repayment period of 12 months can be pushed to the target user, or a credit product with the price of 3 ten thousand and the repayment period of 6 months can be pushed to the target user; if the credit limit information of the target user is f, a credit product with the price of 5 ten thousand and the repayment period of 12 months can be pushed to the target user, or a credit product with the price of 2.5 ten thousand and the repayment period of 6 months can be pushed to the target user; if the credit limit information of the target user is g, credit products with the price of 2 ten thousand and the repayment period of 6 months can be pushed to the target user, or credit products with the price of 1 ten thousand and the repayment period of 3 months can be pushed to the target user; if the credit limit information of the target user is g, credit products with the price of 5000 blocks and the repayment period of 3 months can be pushed to the target user.

Therefore, the higher the credit line of the target user is, the higher the price of the pushed credit product is, the larger the amount of money paid each time is, and the longer the period is; the higher the credit line of the target user is, the smaller the amount of each payment is, and the shorter the period is.

In addition, the credit line information of the target user is determined according to the credit risk assessment result of the target user, the repayment capacity of the target user is determined according to the characteristic information, further, the credit product information pushed for the target user is determined according to the credit line information of the target user and the repayment capacity of the target user, and further, the accuracy of the credit product information pushed for the target user is improved.

As shown in fig. 5, the apparatus 500 includes: an information acquisition module 510 and a risk assessment module 520.

The information obtaining module 510 is configured to obtain feature information of a target user;

the risk assessment module 520 is configured to input the feature information into a pre-established risk assessment model, and output a credit risk assessment result of the target user, where the risk assessment model is obtained by training feature information of different users and credit risk assessment results thereof as training samples.

Optionally, the risk assessment module 520 includes:

and the acquisition submodule is used for acquiring the historical characteristic information of a plurality of users belonging to the same user category.

And the determining submodule is used for determining a credit risk evaluation result of each user according to the historical characteristic information of the user and a preset credit risk evaluation rule corresponding to the user category.

And the risk evaluation submodule is used for training the logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk evaluation result corresponding to the historical characteristic information as training samples to obtain a risk evaluation model corresponding to the user category.

Optionally, the result determination module includes: the first result determining submodule is used for determining the default probability level of the target user according to the credit risk evaluation result of the target user; and the second result determining submodule is used for outputting the credit line information of the target user according to the default probability level of the target user and the preset corresponding relation between the default probability level and the credit line information.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the credit risk assessment method.

An embodiment of the present disclosure further provides an electronic device, including:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to implement the steps of the credit risk assessment method.

FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment. As shown in fig. 6, the electronic device 600 may include: a processor 610, and a memory 620. The electronic device 600 may also include one or more of a multimedia component 630, an input/output (I/O) interface 640, and a communications component 650.

The processor 610 is configured to control the overall operation of the electronic device 600 to complete all or part of the steps of the above-described credit risk assessment method. The memory 620 is used to store various types of data to support operations at the electronic device 600, such as instructions for any application or method operating on the electronic device 600, and instruction-related data, such as application information data, credit investigation information data, etc., required by the credit risk assessment method in the disclosed embodiments. The Memory 620 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 630 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may further be stored in the memory 620 or transmitted through the communication component 650. The audio assembly also includes at least one speaker for outputting audio signals. An input/output (I/O) interface 640 provides an interface between the processor 610 and other interface modules, such as a keyboard, mouse, buttons, and the like. These buttons may be virtual buttons or physical buttons. The communication component 650 is used for wired or wireless communication between the electronic device 600 and other devices. The wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding Communication component 650 may include: Wi-Fi module, bluetooth module, NFC module.

In an exemplary embodiment, the electronic Device 600 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described credit risk assessment method.

In another exemplary embodiment, a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the method of risk described above is also provided. For example, the computer readable storage medium may be the memory 620 described above including program instructions that are executable by the processor 610 of the electronic device 600 to perform the credit risk assessment method described above.

In a possible approach, a block diagram of the electronic device may be as shown in fig. 7. Referring to fig. 7, the electronic device 700 may be provided as a server. Referring to fig. 7, an electronic device 700 includes a processor 710, which may be one or more in number, and a memory 720 for storing computer programs executable by the processor 710. The computer program stored in memory 720 may include one or more modules that each correspond to a set of instructions. Further, the processor 710 may be configured to execute the computer program to perform the steps performed by the server in the above-described credit risk assessment method.

Additionally, the electronic device 700 may also include a power component 730 and a communication component 740, the power component 730 may be configured to perform power management of the electronic device 700, and the communication component 740 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 700. In addition, the electronic device 700 may also include input/output (I/O) interfaces 750. The electronic device 700 may operate based on an operating system stored in the memory 720, such as Windows Server, Mac OSXTM, UnixTM, LinuxTM, and the like.

In another exemplary embodiment, a computer readable storage medium including program instructions, which when executed by a processor, implement the steps performed by the server in the above credit risk assessment method, is also provided. For example, the computer readable storage medium may be the memory 720 described above including program instructions that are executable by the processor 710 of the electronic device 700 to perform the steps of the credit risk assessment method described above.

The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.

In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.

Claims

1. A credit risk assessment method, comprising:

acquiring characteristic information of a target user;

and inputting the characteristic information into a pre-established risk assessment model, and outputting a credit risk assessment result of the target user, wherein the risk assessment model is obtained by training the characteristic information of different users and the credit risk assessment result thereof as training samples.

2. The method according to claim 1, wherein the risk assessment model is a plurality of risk assessment models, and each risk assessment model corresponds to a user category, wherein the user categories are divided according to historical credit information of users;

wherein each risk assessment model is established according to the following ways:

training a logistic regression model by taking the historical characteristic information of each user in the user category and the credit risk assessment result corresponding to the historical characteristic information as training samples to obtain a risk assessment model corresponding to the user category;

3. The method of claim 1, further comprising, prior to said entering said characteristic information into a pre-established risk assessment model:

judging whether the target user accords with a preset admission rule or not;

and if the target user is determined to accord with the access rule, inputting the characteristic information into the risk assessment model.

4. The method according to any one of claims 1-3, further comprising:

determining credit limit information of the target user at least according to a credit risk evaluation result of the target user;

and determining credit product information pushed for the target user according to the credit line information.

5. The method of claim 4, wherein determining the credit line information of the target user based at least on the credit risk assessment result of the target user comprises:

determining the default probability grade of the target user according to the credit risk evaluation result of the target user;

and outputting the credit line information of the target user according to the default probability level of the target user and the preset corresponding relation between the default probability level and the credit line information.

6. The method of claim 4, wherein determining the credit line information of the target user based at least on the credit risk assessment result of the target user comprises:

obtaining repayment capability characteristic information of the target user according to the characteristic information of the target user;

obtaining the repayment capacity grade of the target user according to the repayment capacity characteristic information;

and obtaining the credit line information of the target user according to the repayment ability level of the target user and the preset corresponding relation among the default probability level, the repayment ability level and the credit line information.

7. A credit risk assessment apparatus, the apparatus comprising:

the information acquisition module is used for acquiring the characteristic information of the target user;

and the risk evaluation module is used for inputting the characteristic information into a pre-established risk evaluation model and outputting a credit risk evaluation result of the target user, wherein the risk evaluation model is obtained by training the characteristic information of different users and the credit risk evaluation result thereof as training samples.

8. The apparatus of claim 7, wherein the risk assessment module comprises:

the acquisition submodule is used for acquiring historical characteristic information of a plurality of users belonging to the same user category;

the determining submodule is used for determining a credit risk evaluation result of each user according to the historical characteristic information of the user and a preset credit risk evaluation rule corresponding to the user category;

the risk evaluation submodule is used for taking the historical characteristic information of each user in the user category and the credit risk evaluation result corresponding to the historical characteristic information as training samples to train the logistic regression model so as to obtain a risk evaluation model corresponding to the user category;

9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.

10. An electronic device, comprising:

a memory having a computer program stored thereon;

a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 6.