Credit risk control method and system, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides a credit risk control method and system, electronic equipment and a readable storage medium, and the method comprises the steps of obtaining the credit information of a user based on basic identity information and authorization information, extracting the original features in the credit information, removing invalid features, and enabling the obtained important features to serve as feature data; extracting an initial application limit from the basic credit application information of the user; inputting the feature data of the user into a preset credit risk scoring model to obtain a credit scoring result of the user; obtaining a risk adjustment factor based on the established and trained risk adjustment factor model; and correcting the initial application quota of the user by using the risk adjustment factor. According to the embodiment of the invention, the credit granting level of the user is adjusted according to the risk level of the user soas to further balance the risk and the income, and maximization of the benefit of the lender can be efficiently, automatically and reasonably realized on the premise that the risk is controllable.

Description

technical field [0001] The invention relates to a risk pricing system applied to credit scenarios, and belongs to the technical field of intelligent risk control. Background technique [0002] The determination of traditional credit lines and credit interest rates relies heavily on manual review. After users submit loan applications, on the one hand, banks and other lenders have to spend a lot of manpower and material resources on data review, background interviews, etc. At the same time, corrections to user loan lines are often Relying on relevant industry experience, it is difficult to realize automated, personalized, and rationalized risk pricing based on the user's credit qualifications, making it difficult to maximize the interests of the lender under the premise of controllable risks. On the other hand, individual users / corporate users, etc. Lenders often spend weeks from submitting credit applications to getting approval results, which is a very poor experience. [0...

AI Technical Summary

Problems solved by technology

[0002] The determination of traditional credit lines and credit interest rates relies heavily on manual review. After users submit loan applications, on the one hand, banks and other lenders have to spend a lot of manpower and material resources on data review, background interviews, etc. Relying on relevant industry experience, it is difficult to realize automated, personalized, and rationalized risk pricing based on the user's credit qualifications, so it is difficult to maximize the interests of the lender under the premise of controllable risks. On the other hand, individual users / corporate users, etc. Borrowers often spend several weeks from submitting credit applications to obtaining approval results, which is a very poor experience

[0003] With the continuous precipitation of multi-dimensional data of users and the development of artificial intelligence technology, intelligent risk control technology has begun to receive more and more attention and application. At present, intelligent risk control technology mainly focuses Data, historical credit behavior data, social behavior data, etc.) comprehensively measure the user's credit risk control, thereby replacing manual review, that is, the output of intelligent risk control is often the result of the user's risk level assessment, but it cannot maximize the interests of the lender For example, customer A applies for a loan of 100,000 yuan, and the intelligent risk control rating results show that the customer has a low probability of overdue with a loan of 100,000 yuan, but in fact, customer A has a loan of 150,000 yuan. The probability of is still low, that is, the lender can further pursue the compound interest

Images