Forecasting Financial Distress and Credit Ratings Using Statistical and Soft-Computing Methods
by
Kuldeep Kumar
Associate Professor, Bond University, Gold Coast, Australia

In this paper we have discussed and compared various methods for forecasting financial distress and credit ratings. Some of these methods are based on statistical techniques like logistic regression and discriminant analysis. As computers have become more powerful they have permitted better testing and forecasting the financial distress using soft computing methods like Artificial Neural Network, Chaos theory and fuzzy logic. We have taken numerous financial ratios of a combination of Australian stock exchange and used these techniques to predict financial distress and to determine which companies will be best suited for investment. Similar techniques can be used for predicting bankruptcy amongst Indian companies.

In the liberalized environment, importance of credit rating concept has increased significantly. The objective of the study is also to explore and find out the effect of the financial performance data of a firm on the credit rating of a debt issue of a firm. The study also proposes to capture the relationship, if any, between financial performance data and credit rating given by expert in an appropriate model.

Financial data relevant to a debt issue ratings is obtained from the publications of a premier credit rating agency in India. Data analysis involved building of model using conventional multiple linear dicriminant analysis and Artificial Neural Network Systems.

Findings clearly showed that financial performance data of the company before the issue has significant effect on credit rating by expert. Artificial Neural Networks (ANN) model was found superior to discriminant analysis model. ANN model can be used to increase speed and efficiency of the rating process in practical applications. In addition, if experts provide better-input data, it can be relied upon to provide automatic rating to a significant extent.

Date received: November 13, 2002

Copyright © 2002 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cakd-06.