This paper uses a data mining approach to the prediction of corporate failure. Initially, we use four single classifiers - discriminant analysis, logistic regression, neural networks and C5.0 - each based on two feature selection methods for predicting corporate failure. Of the two feature selection methods - human judgement based on financial theory and ANOVA statistical method - we found the ANOVA method performs better than the human judgement method in all classifiers except discriminant analysis. Among the individual classifiers, decision trees and neural networks were found to provide better results. Finally, a hybrid method that combines the best features of several classification models is developed to increase the prediction performance. The empirical tests show that such a hybrid method produces higher prediction accuracy than individual classifiers.
Bibliographical noteOther Details
This paper describes and evaluates a data mining approach to the prediction of corporate failure. It was published, in an earlier version, at the 20th BCS SGES International Conference in December 2000, where it won a best paper award and was selected to appear as a journal paper in JKBS. The paper combines classification algorithms with business knowledge and human judgment. The results were evaluated, and shown to give good results, using a standard online database on corporate accounts. The topic is part of ongoing work of the Information and Software Engineering research group in the area of knowledge discovery.