Using Machine Learning, Neural Networks and Statistics to Predict Corporate Bankruptcy: A Comparative Study

Recent literature strongly suggests that machine learning approaches to classification outperform “classical” statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees and neural networks in predicting corporate bankruptcy. Linear discriminant analysis represents the “classical” statistical approach to classification, whereas classification trees and neural networks represent artificial intelligence approaches. A proper statistical design is used to be able to test whether observed differences in predictive performance are statistically significant. The dataset consists of two large collections of annual reports from Belgian companies. The first collection contains the reports of 994 industrial companies and the second collection contains the reports of 576 construction companies. We use stratified 10-fold cross-validation on the training set to choose “good” parameter values for the different learning methods.