Method of farmers' multi-layer one-way network piecewise linear credit rating

Abstract

The invention discloses a method of farmers' multi-layer one-way network piecewise linear credit rating and practical applications thereof in farmers' credit rating. According to the invention, first a farmers' credit rating indicator system is constructed into a multi-layer one-way network structure, then a credit rating formula of the farmers' credit rating indicator system is established to perform the credit rating, and finally a piecewise linear classifier is used to perform credit rating classification on results outputted by the multi-layer one-way network. The credit rating method of the invention establishes principles of farmers' credit rating and an evaluation model of the farmers' credit rating one-way network piecewise linear, and discusses properties needed to be satisfied by bank loan credit extension which is based on the farmers' credit rating. Furthermore, the model established on theories is applied to practical farmers' credit rating in Yunan county of Yunfu city of Guangdong province. When credit rating is carried out on farmers in some mountainous counties of our country, an assessment result which corresponds to the practical farmers' credit rating is received with an accuracy rate of 100%.

Description

technical field [0001] The invention relates to the field of credit rating, in particular to a farmer credit rating method. Background technique [0002] At home and abroad, there have been many achievements in the research of enterprise (including commercial banks) credit rating or credit evaluation, and most of the achievements have been commercialized. More representatively, David West (2000) established five neural network credit evaluation models to study the accuracy of commercial bank credit evaluation. He classified the two sets of financial data in Germany and Australia into two types of models, and established five neural network models: multi-layer sensory perceptron, expert hybrid system, radial basis function network, learning vector quantizer and fuzzy Adaptive resonance was compared with five statistical classification models: linear discriminant analysis, Logistic regression model, K nearest neighbor method, kernel density classification method, and classifi...

AI Technical Summary

Problems solved by technology

[0006] At present, my country's research on farmer credit rating has just started, and there are very few literature studies

In the only few documents I have seen, the "models" established are directly transplanted into the credit rating of farmer households by using the existing models that have been widely used in other fields and are very mature. Therefore, in the research methods and There is no innovation in the model

Furthermore, the models given in these literatures have no practical application, nor can they be practically applied, because the data types of the farmer credit rating index set are fundamentally different from those of the original model’s field index set, so of course they cannot be applied. Theoretical discussion

Images