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

35 Pages 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

Date Written: October 2000

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 (October 2000). Available at SSRN: https://ssrn.com/abstract=251082 or http://dx.doi.org/10.2139/ssrn.251082

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

Register to save articles to
your library

Register

Paper statistics

Downloads
1,093
rank
18,577
Abstract Views
4,208
PlumX Metrics
!

Under construction: SSRN citations will be offline until July when we will launch a brand new and improved citations service, check here for more details.

For more information