Credit integral prediction method, credit integral prediction system and related device

Abstract

The invention provides a credit integral prediction method comprising the following steps: extracting each target index from index data of all enterprises by utilizing an XGBOOST algorithm according to the importance degree of each preset index; after the data sets corresponding to the target indexes of all the enterprises of all the categories are obtained, a regression algorithm is used for carrying out model training on the data sets corresponding to all the enterprises of the target categories, and a regression model corresponding to the regression algorithm is obtained; and inputting thehistorical data of any target category of enterprises into the regression model to obtain a credit score prediction result of the target category of enterprises. Therefore, according to the method, the regression model trained by the data sets corresponding to all the enterprises of the target category is utilized to predict the credit score of the enterprise of the target category, and the accuracy of credit score prediction can be improved. The invention also provides a credit score prediction system and device, and a computer readable storage medium, which all have the above beneficial effects.

Description

technical field [0001] The present application relates to the technical field of credit score prediction, and in particular to a credit score prediction method, system, device, and computer-readable storage medium. Background technique [0002] The traditional forecasting of credit score is to use experts to evaluate various indicators of the enterprise (such as the registration period, enterprise size, registered capital, etc.), and then assign a weight to each indicator with the help of expert experience, and finally perform a weighted average of all indicators Get a score, the credit score. However, the above-mentioned approach is highly subjective in terms of the selection of indicators and the assignment of index weights. It completely relies on the experience of experts. It is very likely that important indicators will be omitted and the assignment of index weights will be inaccurate, resulting in accurate credit score prediction. The degree is not high. [0003] The...

AI Technical Summary

Problems solved by technology

However, the above-mentioned approach is highly subjective in terms of the selection of indicators and the assignment of index weights. It completely relies on the experience of experts. It is very likely that important indicators will be missed and the assignment of index weights will be inaccurate, resulting in accurate credit score prediction. degree is not high

Images