Enterprise credit rating evaluation method and device, electronic equipment and medium

Abstract

The invention provides an enterprise credit rating evaluation method and device, electronic equipment and a medium. The method and the device can be used in the financial field or the artificial intelligence field. The method and the device can be applied to a credit system in the financial field, and are particularly applied to enterprise credit rating. The enterprise credit rating evaluation method can comprise the following steps: acquiring sample enterprise credit rating characteristic data; obtaining sample enterprise credit evaluation result data; marking the sample enterprise credit evaluation characteristic data and the sample enterprise credit evaluation result data as a first training data set; based on the first training data set, training through a predetermined algorithm to obtain an enterprise credit rating evaluation model; obtaining credit evaluation characteristic data of the to-be-evaluated enterprise; and inputting the credit rating characteristic data of the to-be-evaluated enterprise into the enterprise credit rating evaluation model to obtain an output credit rating evaluation result, wherein the algorithm is a Stacking ensemble learning algorithm based on a K-fold cross validation method.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and more specifically, to a method, device, electronic device and medium for evaluating an enterprise credit rating. Background technique [0002] The bank's credit business limits the amount of corporate loans mainly based on the credit rating system. The credit rating system fundamentally indicates the size of the corporate default risk. Correspondingly, the accuracy of the rating results directly affects the level of credit risk. Whether the bank funds can operate healthily. [0003] For financial corporate customers, especially commercial banks, the current traditional credit rating evaluation methods are mostly evaluated and predicted from the perspective of accounting, by finding accounting indicators that affect corporate customers' solvency, and then according to the experience of the evaluators themselves. Different weights are set for each degree, and finally t...

AI Technical Summary

Problems solved by technology

[0005] In the traditional credit rating evaluation method, the factors affecting the credit rating evaluation are extremely extensive, and it is difficult to convert all the influencing factors into corresponding accounting indicators

Moreover, the evaluation process is heavily dependent on the work experience of the evaluators themselves, making it difficult to standardize credit rating evaluation

On the other hand, although the existing new credit evaluation methods based on mathematical methods and statistical models reduce the dependence on the evaluators' own business experience to a certain extent, due to the inherent shortcomings of each model, the evaluation accuracy needs to be improved

Images