Method, device and equipment for predicting credit default probability of small and micro enterprises, and storage medium

Abstract

The invention relates to the technical field of computers, discloses a method, a device and equipment for predicating the credit default probability of small and micro enterprises, and a storage medium, and aims to solve the problems of data scarcity, incompleteness, insufficient historical information precipitation and the like in small and micro enterprise credit businesses of financial institutions. According to the main scheme, the transfer learning-based small and micro enterprise credit default probability prediction method comprises the following steps: 1, obtaining a credit application request of a small and micro enterprise; 2, extracting current application feature information in the credit application request; 3, performing combined feature extraction on the application feature information of the current small and micro enterprises through a source domain integrated learning model, and marking the leaf node position to which a prediction probability value obtained by calculation of each tree in the source domain integrated learning model belongs as 1 to obtain a combined feature; and 4, carrying out credit default probability prediction through a target domain learning model according to the extracted combined features, and obtaining a prediction result of the credit default probability of the small and micro enterprises.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method, device, equipment and storage medium for predicting the probability of credit default of small and micro enterprises. Background technique [0002] Since the rapid development of mobile Internet technology, the contactless credit business has exploded, and financial institutions have made breakthroughs in the transformation of retail strategies. However, in the past, it was mainly for personal consumption loans. After nearly a decade of development, personal consumption loans have faced excessive leverage and growth. Weakness, profit shrinkage, regulatory tightening and other difficulties, especially the supervision has repeatedly emphasized that it is not appropriate to rely on the development of consumer finance to expand consumption. Since last year, various regulatory agencies have continued to vigorously support the improvement of financial services for t...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to propose a method, device, equipment, and storage medium for predicting the probability of credit default of small and micro enterprises, aiming to solve the problems of data scarcity, incompleteness, and insufficient precipitation of historical information faced by financial institutions in the credit business of small and micro enterprises , to improve the effect of small and micro enterprise credit risk control models, thereby improving the level of financial institutions serving the real economy

Images