A study on credit risk early warning model of commercial banks based on BP neural network

With the development of financial liberty and integration, Chinese commercial bank will be confronted with severe circumstance in the course of financial revolution, which will bring about the commercial bank's more and more credit risk. It is very necessary to research and grasp completely and systematically the characteristic, manifest and reason, and construct the early warning system of the commercial bank's credit risk to control completely the risk. Whether in thoughts or technology, application of the Artificial Neural Network in early warning of commercial bank credit risk is a breakthrough. Commercial bank credit risk management can be divided into two sections, early warning before loan and early warning after loan. The purpose of this paper is to study the early warning after loan. We discuss the early warning signal about financial factor, using the factor analysis in SPSS. Then we introduce the back-propagation neural network to design network framework, carry on the network training and test, then make positive analysis to the samples with Matlab. According to the results of B-P model analysis, carry on the general analysis, thus achieve the goal of credit loan early warning.