Research on Chinese Listed Company´s Financial Crisis Based on SVM Classification

SVM based model is constructed for predicting performances of Chinese listed companies. The paper firstly uses factor analysis, equal value difference test and correlation test to sieve the financial indicators and corporate governance variables separately for representative variables, and then uses the method of support vector machine for an empirical analysis. The research shows the model of SVM is superior. And through the comparison with the model based on financial indicators, we find that the model incorporating corporate governance variables has a more excellent prediction performance.