In-loan behavior monitoring method and system

Abstract

The invention discloses an in-loan behavior monitoring method and system, and relates to the field of information processing and application, and the method comprises the following steps: obtaining adata set formed by business types and historical behavior characteristic data of customers, then utilizing a pre-trained logistic regression prediction model corresponding to the business types to calculate and obtain default probability of the customers according to the data set, and finally performing in-loan behavior monitoring according to the default probability. A default risk of a client ispredicted according to historical behavior characteristic data of the client in loan; the method evaluates the repayment capability, repayment willingness and the like of the client, monitors the in-loan behaviors according to the default probability, timely takes effective prevention measures for high-risk clients, accurately positions client groups, improves the loan effectiveness, monitors thein-loan behaviors, avoids the influence of human factors, improves the review efficiency and increases the effective credit amount. The method can be widely applied to the credit field.

Description

technical field [0001] The invention relates to the field of information processing and application, in particular to a method and system for monitoring loan behavior. Background technique [0002] In recent years, with the rapid development of Internet finance and the explosive growth of behavioral data accumulated on the Internet, relying on massive data, the volume of Internet loan business of customers has increased year by year. However, at present, after the pre-loan evaluation process is completed and the loan is released, the customer may still default during the repayment process. In order to reduce the risk of default in the loan, at present, business personnel mostly determine the repayment ability of the loaned customer based on human experience. Repayment intentions are used to assess the risk of default, so there is no effective way to monitor loan behaviors to reduce loan business risks. Due to the greater influence of human factors, the reliability of the rev...

AI Technical Summary

Problems solved by technology

However, at present, after the pre-loan evaluation process is completed and the loan is released, the customer may still default during the repayment process. In order to reduce the risk of default in the loan, at present, most of the business personnel determine the repayment ability of the loaned customer based on human experience. Repayment intentions are used to assess the risk of default, so there is no effective way to monitor loan behaviors to reduce loan business risks. Due to the greater influence of human factors, the reliability of the review results is low, and the review efficiency is low, resulting in bad debts. The number of accounts increased, and the amount of effective loans decreased

Images