Comparative analysis of artificial neural network models: application in bankruptcy prediction

Author

Charalambous, Chris ; Charitou, Andreas ; Kaourou, Froso

Author_Institution

Dept. of Bus. Adm., Cyprus Univ., Nicosia, Cyprus

Volume

6

fYear

1999

fDate

36342

Firstpage

3888

Abstract

This study compares the predictive performance of three neural network methods, namely the learning vector quantization, radial basis function, the feedforward network that uses the conjugate gradient optimization algorithm, with the performance of the logistic regression and the standard backpropagation algorithm. All these methods are applied to a dataset of 139 matched-pairs of bankrupt and nonbankrupt US 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 from the feedforward method using the standard backpropagation algorithm

Keywords

conjugate gradient methods; feedforward neural nets; finance; forecasting theory; learning (artificial intelligence); optimisation; radial basis function networks; vector quantisation; artificial neural network models; bankruptcy prediction; conjugate gradient optimization algorithm; feedforward method; feedforward network; learning VQ; learning vector quantization; logistic regression; logistic regression method; matched-pairs; neural network prediction; radial basis function; standard backpropagation algorithm; Artificial neural networks; Backpropagation algorithms; Feedforward neural networks; Intelligent networks; Logistics; Neural networks; Optimization methods; Predictive models; Statistical analysis; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.830776

Filename

830776