Neural Networks: A New Tool for Predicting Thrift Failures

Authors

Linda Salchenberger, Marquette UniversityFollow
E. Mine Cinar, Loyola University Chicago
Nicholas A. Lash, Loyola University Chicago

Document Type

Article

Language

eng

Publication Date

7-1992

Publisher

Wiley

Source Publication

Decision Sciences

Source ISSN

0011-7315

Abstract

A neural network model that processes input data consisting of financial ratios is developed to predict the financial health of thrift institutions. The network's ability to discriminate between healthy and failed institutions is compared to a traditional statistical model. The differences and similarities in the two modelling approaches are discussed. The neural network, which uses the same financial data, requires fewer assumptions, achieves a higher degree of prediction accuracy, and is more robust.

Comments

Decision Sciences, Vol. 23, No. 4 (July 1992): 899-916. DOI.

Linda M. Salchenberger was affiliated with Loyola University of Chicago at the time of publication

Recommended Citation

Salchenberger, Linda; Cinar, E. Mine; and Lash, Nicholas A., "Neural Networks: A New Tool for Predicting Thrift Failures" (1992). Management Faculty Research and Publications. 283.
https://epublications.marquette.edu/mgmt_fac/283