Neural network models and the prediction of bank bankruptcy

The number of failed banks has reached a high unparalleled since the great Depression. Research in developing predictive models for bank failures is therefore warranted and desirable in this turbulent period. This paper presents a neural network approach to bank failures prediction and compares its performance with existing models. Empirical results show that among alternative models, neural networks is a competitive instrument for evaluating the financial condition of a bank. The study concludes with a discussion on the potential and limitations of neural networks as a general modelling tool for financial applications.