Efficiency of Machine Learning Techniques in Bankruptcy Prediction

by Sotos B. Kotsiantis of the Technological Educational Institute of Patras,
Dimitris Tzelepis of the Technological Educational Institute of Patras,
Evangelos P. Koumanakos of the National Bank of Greece, and
Vasilios Tampakas of the Technological Educational Institute of Patras

July 11, 2005

Abstract: Prediction of corporate bankruptcy is a phenomenon of increasing interest to investors/creditors, borrowing firms, and governments alike. Timely identification of firms' impending failure is indeed desirable. The scope of the research reported here is to investigate the efficiency of machine learning techniques in such an environment. To this end, a number of experiments have been conducted using representative learning algorithms, which were trained using a data set of 150 failed and solvent Greek firms in the recent period 2003-2004. It was found that learning algorithms could enable users to predict bankruptcies with satisfying accuracy long before the final bankruptcy.

Keywords: supervised machine learning algorithms, prediction of bankruptcy.

Books Referenced in this Paper:  (what is this?)

Download paper (104K PDF) 11 pages

[Home] [Credit Scoring Papers]

[ Home ] [ Up ]

Please contact me with problems or suggestions.
Copyright © 2000-2008 DefaultRisk.com
Last modified: May 15, 2008