A comparative study on the bankruptcy prediction power of statistical models and AI models: MDA, inductive learning and neural networks

This paper is concerned with analyzing the bankruptcy prediction power of three methods: Multivariabe Discriminant Analysis (MDA), Inductive Learning, Neural Network. MDA has been famous for its effectiveness for predicting bankruptcy in accounting fields. However, it requires rigorous statistical assumptions, so that violating one of the assumptions may result in biased outputs. In this respect, the paper alternatively proposes the use of two AI models for bankruptcy prediction-inductive learning and neural network. To compare the performance of those two AI models with that of MDA, massive experiments have been performed with a number of Korean bankrupt cases. Experimental results show that AI models proposed in this study can yield more robust and generalizing bankruptcy prediction than the conventional MDA can do. [In Korean.]