User credit score prediction method and related equipment

Abstract

The invention discloses a user credit score prediction method and related equipment which can be applied to the field of artificial intelligence and the field of finance. The user credit score prediction method comprises the following steps: performing feature fusion on source domain user initial data and target domain user data by using a preset domain adaptive algorithm to obtain a to-be-trained source domain data set, wherein the to-be-trained source domain data set comprises source domain user target data corresponding to the source domain user initial data; acquiring a target user credit score prediction model by using the source domain user target data and the target domain user data; and acquiring a user credit score prediction result corresponding to the target user data through the target user credit score prediction model. According to the invention, the feature fusion is carried out on the data of the source domain and the target domain through the preset domain adaptive algorithm, and knowledge migration between the data of different domains is realized, so that the credit score prediction of the trained target user credit score prediction model on the target user data is more accurate.

Description

technical field [0001] The present disclosure relates to the field of data processing, in particular to a user credit score prediction method and related equipment. Background technique [0002] With the vigorous development of Internet technology in the financial industry, Internet financial services have been widely used. For Internet financial services, customer credit scores are an important prerequisite for banks and other financial institutions to conduct business smoothly. [0003] However, although the bank has a large amount of historical user data, due to the rapid development of the bank's current financial business and the variety of types, there is less training data that can be directly used to build a credit scoring model. Whether it is directly using historical user data Or use a small amount of new business data to construct a credit score prediction model, and the accuracy of the constructed model for credit score prediction is not high. Contents of the ...

AI Technical Summary

Problems solved by technology

[0003] However, although the bank has a large amount of historical user data, due to the rapid development of the bank's current financial business and the variety of types, there are few training data that can be directly used to build a credit scoring model. Whether it is directly using historical user data Or use a small amount of new business data to construct a credit score prediction model. The accuracy of the constructed model for credit score prediction is not high

Images