NEURAL-NETWORK PERFORMANCE ON THE BANKRUPTCY CLASSIFICATION PROBLEM

Due to the recent changes in the world economy and as more firms, large and small, seem to fail now than ever, the bankruptcy classification problem is of increasing importance. Unfortunately, there are no easy-to-use and accurate tools to help make bankruptcy classification decisions. In this study, artificial neural network (ANN) technology is used to predict the going concern of firms based on financial ratios of 300 companies. The results indicate that ANN is as accurate or more accurate as a multiple regression model in predicting bankruptcy in addition to being easier to use and readily adapting to the changing environment.