Financial Distress Prediction for Chinese Listed Manufacturing Companies

AbstractFinancial distress prediction can be formulated as a classification problem and accomplished by advanced data mining techniques. In classification based on multiple criteria linear programming (MCLP), we need to find the optimal solution as a classifier, by solving the MCLP problem. However, the errors can be caused by a fixed cutoff between a “good” group and a “bad” group by MCLP structure. In many applications, such as credit card account classification and bankruptcy prediction, how to handle two types of error is a key issue. Using the structure of multiple criteria and multiple constraint levels linear programming (MC2LP), which allows alterable cutoff, two types of errors can be systematically corrected. In order to do so, a penalty is imposed to find the potential solution for all possible trade-offs in solving MC2LP problem. Real dataset of Chinese listed manufacturing companies is used to validate MC2LP method. Comparison with classical optimization-based method SVM and MCLP is also provided