Constructing Financial Distress Prediction Model using Group Method of Data Handling Technique
Companies in financial distress make the creditors, shareholders, employees, investors and other participants of the related firms suffer great losses. In order to prevent the companies run into bankruptcy, financial distress prediction has been a useful tool for distinguishing companies in financial distress from those healthy. Statistical methods and artificial intelligence techniques have been widely used to deal with this issue. Many studies indicated that artificial neural networks outperform many statistical methods. However, artificial neural networks have the drawback of failing to interpret the classification results. This paper uses an artificial intelligence technique- group method of data handling technique to overcome this drawback. The sample data are collected from Taiwan listed companies in the Taiwan Stock Exchange Corporation. The result illustrates that the accuracy rates of classification of group method of data handling models are larger than 90％ and the models of the group method of data handling obtain better accuracy than the models of discriminant analysis and logistic regression.
Financial distress prediction Group method of data handling Artificial neural network
CHIEN-HUI YANG MOU-YUAN LIAO PIN-LUN CHEN MEI-TING HUANG CHUN-WEI HUANG JIA-SIANG HUANG JUI-BIN CHUNG
Department of Business Administration, Yuanpei University, Hsinchu, Taiwan 30015, ROC Department of Finance, Yuanpei University, Hsinchu, Taiwan 30015, ROC
国际会议
2009 International Conference on Machine Learning and Cybernetics(2009机器学习与控制论国际会议)
保定
英文
2897-2902
2009-07-12（万方平台首次上网日期，不代表论文的发表时间）