Title :
Research on Chinese Listed Company´s Financial Crisis Based on SVM Classification
Author :
Zhu, Jun ; Su, Yanli
Author_Institution :
Sch. of Bus. & Adm., Northeastern Univ., Shenyang, China
Abstract :
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.
Keywords :
financial data processing; pattern classification; support vector machines; Chinese listed company; corporate governance; correlation test; empirical analysis; equal value difference test; factor analysis; financial crisis; support vector machine classification; Accuracy; Analytical models; Companies; Kernel; Predictive models; Profitability; Support vector machines; financial crisis; support vector machine; warning;
Conference_Titel :
E-Business and E-Government (ICEE), 2010 International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-0-7695-3997-3
DOI :
10.1109/ICEE.2010.628