Comparative Analysis of Artificial Neural Network Models: Application in Bankruptcy Prediction

Posted: 10 Feb 2001

See all articles by Christakis Charalambous

Christakis Charalambous

University of Cyprus - Department of Public and Business Administration

Andreas Charitou

University of Cyprus

Froso Kaourou

University of Cyprus

Multiple version iconThere are 2 versions of this paper

Abstract

This study compares the predictive performance of three neural network methods, namely the Learning Vector Quantization, the Radial Basis Function, and the Feedforward network that uses the conjugate gradient optimization algorithm, with the performance of the logistic regression and the backpropagation algorithm. All these methods are applied to a dataset of 139 matched-pairs of bankrupt and non-bankrupt U.S firms for the period 1983-1994. The results of this study indicate that the contemporary neural network methods applied in the present study provide superior results to those obtained from the logistic regression method and the backpropagation algorithm.

JEL Classification: M41, G33

Suggested Citation

Charalambous, Christakis and Charitou, Andreas and Kaourou, Froso, Comparative Analysis of Artificial Neural Network Models: Application in Bankruptcy Prediction. Available at SSRN: https://ssrn.com/abstract=254801

Christakis Charalambous

University of Cyprus - Department of Public and Business Administration ( email )

75 Kallipoleos Street
P.O. Box 20537
Nicosia CY-1678
CYPRUS
00357-2-892258 (Phone)
00357-2-339063 (Fax)

Andreas Charitou (Contact Author)

University of Cyprus ( email )

75 Kallipoleos Street
P.O. Box 20537
Nicosia CY-1678
Cyprus
+357 2 893624 (Phone)
+357 2 895030 (Fax)

Froso Kaourou

University of Cyprus

75 Kallipoleos Street
Nicosia CY 1678, Nicosia P.O. Box 2
Cyprus

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
1,873
PlumX Metrics