Credit risk determination and data processing method and equipment, medium and program product

Abstract

The embodiment of the invention provides a credit risk determination and data processing method and equipment, a medium and a program product. According to the embodiment of the invention, the method comprises the steps of carrying out the feature extraction of the credit application data of a to-be-tested user and the credit application data of a sample user, and determining the credit features of the to-be-tested user and the credit features of the sample user, calculating the similarity between the to-be-tested user and the sample user according to the credit characteristics of the to-be-tested user and the credit characteristics of the sample user, and determining the risk attribute of the to-be-tested user according to the similarity between the to-be-tested user and the sample user and the risk attribute of the sample user. As the similarity between the to-be-tested user and the sample user is introduced during credit risk prediction of the to-be-tested user, the reason that the to-be-tested user is determined as the current risk attribute can be explained according to the similarity between the to-be-tested user and the sample user, so that the credit risk prediction result has interpretability; and the requirement of a credit risk control scene on interpretability can be met.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a credit risk determination and data processing method, device, medium and program product. Background technique [0002] The deep learning model can have stronger representation ability, and has achieved better model effects in many scenarios. However, on the one hand, the deep learning model has a relatively large demand for sample data, and the sample size in the credit risk control scenario is generally difficult to meet the data requirements of the deep network; on the other hand, the deep learning model is not interpretable enough to Meet the requirements of credit risk control scenarios for interpretability. Contents of the invention [0003] Various aspects of the present application provide a credit risk determination and data processing method, device, storage medium, and program product to meet the interpretability requirements of credit risk contr...

AI Technical Summary

Problems solved by technology

However, on the one hand, the deep learning model has a relatively large demand for sample data, and the sample size in the credit risk control scenario is generally difficult to meet the data requirements of the deep network; on the other hand, the deep learning model is not interpretable enough to Meet the interpretability requirements of the credit risk control scenario

Images