Model selection for financial distress classification

This paper describes results concerning the robustness and generalization capabilities of a supervised machine learning methods for classifying the financial health of French companies. Financial data was obtained from Diana, a large database containing-financial statements of French companies. Classification accuracy is evaluated with Artificial Neural Networks, TreeNet, Random Forests and Liner Genetic Programs (LGPs). LGPs have the best performance accuracy in both balanced data and unbalanced dataset. Our results demonstrate the potential of using learning machines in solving important economics problems such as financial distress classification. Feature selection is as important for financial distress classification as;it is for many other problems. We present several feature selection methods for financial distress classification. It is demonstrated that, with appropriately chosen features, financial health of a company can be detected. Experiments on Diana dataset have been carried out to assess the effectiveness of this criterion.