Credit state monitoring system and monitoring method

Abstract

The invention discloses a credit state monitoring system and monitoring method, and relates to the field of credit monitoring. The method comprises the following steps: S1, collecting a large number of credit reports as unmarked samples and preprocessing the samples; S2, setting credit evaluation indexes in advance; S3, analyzing and processing the information through a fuzzy optimization model; S4, classifying the associated data to generate a labeled sample set; S5, generating a multi-class classification model by taking part of the sample set as a training set; S6, taking the rest part of the sample set as a test set to test the trained classification model; and S7, importing the labeled sample set into the tested classification model to output a credit state monitoring grade. The collected unmarked samples are preliminarily screened through the fuzzy optimization model, SVM classification training is performed on the sample set to generate the classification model, the classification model is tested through the remaining sample set, the optimal classification model is obtained, the enterprise credit evaluation efficiency is improved, and the monitoring strength is enhanced.

Description

technical field [0001] The invention belongs to the technical field of credit monitoring, and in particular relates to a credit state monitoring system and a monitoring method. Background technique [0002] Enterprise credit generally refers to the credit granted by one enterprise legal person to another enterprise legal person, and its essence is the currency loan from the seller enterprise to the buyer enterprise. It includes the credit sales of manufacturing enterprises to customers with the nature of corporate legal persons in credit management, that is, product credit sales. In the process of product credit sales, creditors are usually material suppliers, product manufacturers and wholesalers, while buyers are the beneficiaries of product credit sales, and they are various corporate customers or agents. The buyer obtains the credit granted by the seller in the name of his own business. Enterprise credit also involves commercial banks, finance companies, and other fina...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a credit status monitoring system and monitoring method, which first preliminarily screens the collected unlabeled samples through the fuzzy optimization model, generates a labeled sample set, and performs SVM classification training on a part of the labeled sample set to generate Classification model, and test the classification model with the remaining sample set to obtain the optimal classification model, which solves the existing problems of imperfect credit evaluation and inaccurate monitoring of enterprises

Images