Artificial Neural Networks to Evaluate Bank Financial Condition -- a Comparison of Relative Costs of Misclassification

Posted: 10 Feb 1997

See all articles by Ram S. Sriram

Ram S. Sriram

Georgia State University

Harlan L. Etheridge

University of Louisiana at Lafayette - Department of Accounting

Date Written: July 1996

Abstract

This study compares the financial distress classification accuracy of two traditional analytical techniques for evaluating financial distress models: logit analysis and multiple discriminant analysis (MDA) to the less restrictive and non-parametric computer-aided techniques, Artificial Neural Networks (ANNs). The study evaluates the techniques both for their overall classification accuracy and type I and type II misclassification rates. Five different ANNs were used because of their suitability for classification-type problems. The techniques were tested on select financial ratios on four areas of a bank's financial performance on 994 financially healthy and 145 financially distressed banks. The results indicated that logit and MDA to have lower overall error rates than ANNs. However, when the relative costs of misclassification were compared, ANNs, in general, performed better than logit and MDA.

JEL Classification: C10, G33, M41

Suggested Citation

Sriram, Ram S. and Etheridge, Harlan L., Artificial Neural Networks to Evaluate Bank Financial Condition -- a Comparison of Relative Costs of Misclassification (July 1996). Available at SSRN: https://ssrn.com/abstract=2873

Ram S. Sriram (Contact Author)

Georgia State University ( email )

P.O. Box 4050
Atlanta, GA 30302-4050
United States
404-651-4464 (Phone)
404-651-1033 (Fax)

Harlan L. Etheridge

University of Louisiana at Lafayette - Department of Accounting ( email )

P.O. Box 43450
Lafayette, LA 70504-3450
United States
337-482-6206 (Phone)
337-482-5906 (Fax)

Register to save articles to
your library

Register

Paper statistics

Abstract Views
2,223
PlumX Metrics