A Heuristic Model for Predicting Bankruptcy

Bankruptcy prediction is one of the major business classification problems. The main purpose of this study is to investigate Kohonen self-organizing feature map in term of performance accuracy in the area of bankruptcy prediction.  A sample of ۱۰۸ firms listed in Tehran Stock Exchange is used for the study. Our results confirm that Kohonen network is a robust model for predicting bankruptcy in today’s fast changing business environment  

Keywords:

Bankruptcy , Prediction , Neural Network , Back-propagation , Kohonen network