Method and device for loan customer credit scoring

Abstract

Embodiments of the invention disclose a method and a device for loan customer credit scoring, and relates to the field of data processing. The method and the device can improve data dimension of credit scoring model analysis and accuracy of credit scoring results of loan customers. The method includes: obtaining at least one category of customer information of a sample customer, wherein the at least one category of customer information is associated with a unique identification code of the sample customer; preprocessing the customer information of each category to obtain sample data; accordingto the sample data corresponding to the customer information of each category and default information of the sample customer, modeling to generate a scoring model corresponding to the customer information of each category; obtaining a credit scoring model by fusing the scoring models corresponding to the customer information of each category; inputting the customer information of the customer tobe evaluated into the credit scoring model, and calculating the default information of the customer to be evaluated.

Description

technical field [0001] The embodiments of the present invention relate to the field of data processing, and in particular to a method and device for credit scoring of loan customers. Background technique [0002] The rapid rise of P2P and other Internet credit products has given borrowers more choices with their fast and convenient application methods. At the same time, efficient approval and high-quality loan services have directly increased customer favorability. Traditional commercial banks have complex loan approval procedures, time-consuming, high labor costs, low loan service efficiency, strong subjective factors, high risks, and a low degree of matching between the actual loan amount and the customer's real credit. These factors make the bank's credit business in the Internet The huge impact of the times. [0003] Traditional commercial banks usually use information such as user credit reports and adopt complex audit procedures to evaluate users' credit and approve c...

AI Technical Summary

Problems solved by technology

Internet finance, on the other hand, mainly uses historical consumption behaviors and user personal credit information, and mainly uses statistical methods such as discriminant analysis, linear regression, and Logistic regression to construct a credit scoring model. The data dimension of the credit scoring model constructed in the prior art is relatively low. Lead to poor model accuracy, which ultimately affects the credit scoring results for loan customers

In addition, most of the modeling methods of existing schemes are linear modeling methods, but in practice, the relationship between the factors that affect the user's personal credit and the personal credit score is not a simple linear relationship, and is generally non-linear, so user information cannot be accurately reproduced Relationship with credit score, resulting in poor model accuracy

Images