Comparison of different intelligent methods in predicting financial failure of listed companies

摘要：

Financial failure prediction can provide early warning signal, thus is help for controlling financial risk. This paper investigates the effectiveness of intelligent classification methods in predicting financial failure of listed companies. The empirical result indicates that the prediction accuracy of support vector machine (SVM) is higher than that of back-propagation neural network (BPNN) and decision tree (DT) and Logit. Because of the structure risk minimization principle(SRM),SVM can still preserve prediction good performance despite small sample of Chinese special treated companies. DT can discover useful knowledge for financial failure decision.

关键词： Predict financial failure listed companies intelligent classification methods

作者: Cuijuan Li Xinping Song

作者单位: Business School Shanghai Institute of Foreign Trade,Shanghai, P. R. China Business and Management School Donghua University Shanghai, P. R. China

会议类型: 国际会议

会议名称: 2007 Conference on Systems Science, Management Science and System Dynamics(第二届系统科学、管理科学与系统动力学国际会议)

会议地点: 上海

会议语种:英文

页码: 1021-1026

在线出版日期: 2007-10-19（万方平台首次上网日期，不代表论文的发表时间）