User repayment model generation method and device and electronic equipment

Abstract

The invention relates to a user repayment model generation method and device, electronic equipment and a computer readable medium. The method comprises the steps of preprocessing multiple pieces of user financial data, and forming a training data set, a test data set and a verification data set, and wherein the user financial data comprise user loan data, user feature data and user basic data; training a machine learning model through the training data set to generate an initial user repayment model; performing cross validation on the initial user repayment model through the test data set andthe validation data set to generate a validation result; and when the verification result meets a preset strategy, generating a user repayment model. According to the user repayment model generation method and device, the electronic equipment and the computer readable medium, the accurate and efficient user repayment model can be established, the behavior of the user can be evaluated based on theuser repayment model, and human resource waste of financial service enterprises is reduced.

Description

technical field [0001] The present disclosure relates to the field of computer information processing, in particular, to a user repayment model generation method, device, electronic equipment and computer readable medium. Background technique [0002] For companies that provide financial services, the biggest risk they face is that users fail to repay debts or bank loans in a timely and full amount due to various reasons. In the existing technology, after a user borrows from a financial service company, the financial company will track the user's repayment status, and within the first time threshold of the user's overdue repayment (the user is in the M2 stage), by evaluating the user's According to the repayment situation, various strategies are launched to urge users to make repayments. [0003] The repayment rate of users currently in arrears is about 12%-14% during the M2 period, and most users will overdue their arrears to a higher age. At present, users who are in the...

AI Technical Summary

Problems solved by technology

[0004] Since user arrears mainly need to be managed manually after the loan, for managers, it takes a lot of time to communicate and coordinate. Once the communication and coordination decrease, the recovery of arrears will be affected. If a large amount of communication and coordination work is carried out The current post-loan management method of user arrears requires a lot of human resources for processing, which adds a lot of operating costs to financial service companies

Images