An integrative model with subject weight based on neural network learning for bankruptcy prediction
- 31 January 2009
- journal article
- Published by Elsevier BV in Expert Systems with Applications
- Vol. 36 (1), 403-410
- https://doi.org/10.1016/j.eswa.2007.09.060
Abstract
This study proposes an integration strategy regarding how to efficiently combine the currently-in-use statistical and artificial intelligence techniques. In particular, by combining multiple discriminant analysis, logistic regression, neural networks, and decision trees induction, we introduce an integrative model with subject weight based on neural network learning for bankruptcy prediction. The strength of the proposed model stems from differentiating the weights of the source methods for each subject in the testing data set. That is, the relative weights consist of N by I matrix, where N denotes the number of subjects and I denotes the number of the source methods. The experiments using a real world financial data indicate that the proposed model can marginally increase the prediction accuracy compared to the source methods. The integration strategy can be useful for a dichotomous classification problem like bankruptcy prediction since prediction can be improved by taking advantage of existing and newly emerging techniques in the future.Keywords
This publication has 22 references indexed in Scilit:
- New evolutionary bankruptcy forecasting model based on genetic algorithms and neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Credit scoring and rejected instances reassigning through evolutionary computation techniquesExpert Systems with Applications, 2003
- Bankruptcy prediction for credit risk using neural networks: A survey and new resultsIEEE Transactions on Neural Networks, 2001
- Bankruptcy prediction of financially stressed firms: an examination of the predictive accuracy of artificial neural networksIntelligent Systems in Accounting, Finance and Management, 2001
- Comparative Analysis of Artificial Neural Network Models: Application in Bankruptcy PredictionAnnals of Operations Research, 2000
- A case-based reasoning approach to bankruptcy prediction modelingIntelligent Systems in Accounting, Finance and Management, 1997
- Predicting Corporate Failure Using a Neural Network ApproachIntelligent Systems in Accounting, Finance and Management, 1995
- Neural Networks, Decision Tree Induction and Discriminant Analysis: an Empirical ComparisonJournal of the Operational Research Society, 1994
- Financial Ratios, Discriminant Analysis and the Prediction of Corporate BankruptcyThe Journal of Finance, 1968
- Financial Ratios As Predictors of FailureJournal of Accounting Research, 1966