Munich Personal RePEc Archive

Bankruptcy prediction and neural networks: The contribution of variable selection methods

du Jardin, Philippe (2008): Bankruptcy prediction and neural networks: The contribution of variable selection methods. Published in: Proceedings of the Second European Symposium on Time Series Prediction (Estsp 2008), Helsinki University of Technology, Porvoo, Finland, (2008): pp. 271-284.

[img]
Preview
PDF
MPRA_paper_44384.pdf

Download (91kB) | Preview

Abstract

Of the methods used to build bankruptcy prediction models in the last twenty years, neural networks are among the most challenging. Despite the characteristics of neural networks, most of the research done until now has not taken them into consideration for building financial failure models, nor for selecting the variables to be included in the models. The aim of our research is to establish that to improve the prediction accuracy of the models, variable selection techniques developed specifically for neural networks may well offer a useful alternative to conventional methods.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.