Applying Backpropagation Neural Networks to Bankruptcy Prediction

Bankruptcy prediction is an important classification problem for a business, and has become a major concern of managers. In this paper, two well-known backpropagation neural network models serving as data mining tools for classification problems are employed to perform bankruptcy forecasting: one is the backpropagation multi-layer perceptron, and the other is the radial basis function network. In particular, the radial basis function network can be treated as a fuzzy neural network. Through examining their classification generalization abilities, the empirical results from the data resources consisting of bankrupt and nonbankrupt firms in England, demonstrated that the radial basis function network outperforms the other classification methods, including the multi-layer perceptron, the multivariate discriminant analysis, and the probit method.