Applying decision tree to predict bankruptcy

Bankruptcy is one of the most important considered issues in financial management and investing. Investors always try to predict probability of bankruptcy in order to prevent wasting their capital. Therefore they are search for methods to forecast a potential crisis in the bankruptcy prediction domain. Data mining is an approach which produces prediction models in different grounds by using statistical techniques and artificial intelligence. In this study, the Clementine software and the method of classification and regression tree are used for mining financial variables. The predictor variables are collected from financial statements of firms accepted in Tehran Stock Exchange during the 1996 to 2009. The 94.5% accuracy of the model and extracted rules indicate that the suggested method has an acceptable efficiency to predict bankruptcy. Also the most important financial ratios are determined in decision making.