Comparative Analysis of Corporate Failure Prediction Methods: Evidence from Chinese Firms

  • Authors:

  • Haicong Yang

  • Affiliations:

  • Hubei University of Economics, Wuhan, China 430000

  • Venue:
  • ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper examines four most popular alternative methods that have been applied in financial failure prediction: linear discriminant analysis, logit analysis, neural networks and support vector machine. The main purpose is to make comparisons of the prediction abilities among different methods. It was implemented by using the Chinese firms data one, two and three years prior to failure in the empirical analysis. The results indicate that the classification accuracy of support vector machine is the highest.