Original Articles

The use of neural networks in predicting company failure

Published in: De Ratione
Volume 8 , issue 2 , 1994 , pages: 57–78

DOI: 10.1080/10108270.1994.11435050

Author(s): John Arron Graduate School Of Business Administration University of the Witwatersrand, South Africa , Merle Sandler Graduate School Of Business Administration University of the Witwatersrand, South Africa

Download full text Get new issue alerts

Abstract

This study investigated the use of neural networks as a tool for predicting company failure. The predictive power of neural networks was compared with more established methodologies in the field of company failure, namely multiple discriminant analysis and logistic regression analysis.

« The South African audit report: an empirical investigation of the positive perceptions gap

A review of the efficiency of the Johannesburg Stock Exchange »