Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience)

Abstract This study analyzes the comparison between traditional statistical methodologies for distress classification and prediction, i.e., linear discriminant (LDA) or logit analyses, with an artificial intelligence algorithm known as neural networks (NN). Analyzing well over 1,000 healthy, vulnerable and unsound industrial Italian firms from 1982–1992, this study was carried out at the Centrale dei Bilanci in Turin, Italy and is now being tested in actual diagnostic situations. The results are part of a larger effort involving separate models for industrial, retailing/trading and construction firms. The results indicate a balanced degree of accuracy and other beneficial characteristics between LDA and NN. We are particularly careful to point out the problems of the ‘black-box’ NN systems, including illogical weightings of the indicators and overfitting in the training stage both of which negatively impacts predictive accuracy. Both types of diagnoslic techniques displayed acceptable, over 90%, classificalion and holdoul sample accuracy and the study concludes that there certainly should be further studies and tests using the two lechniques and suggests a combined approach for predictive reinforcement.

[1]  Kar Yan Tam,et al.  A Comparative Analysis of Inductive-Learning Algorithms , 1993 .

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Gordon V. Karels,et al.  Multivariate Normality and Forecasting of Business Bankruptcy , 1987 .

[4]  Ingoo Han,et al.  An empirical investigation of some data effects on the classification accuracy of probit, ID3, and neural networks* , 1992 .

[5]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[6]  Carol E. Brown,et al.  Artificial neural networks applied to ratio analysis in the analytical review process , 1993 .

[7]  Edward I. Altman,et al.  FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY , 1968 .

[8]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[9]  David W. Wright,et al.  Using Artificial Neural Networks to Pick Stocks , 1993 .

[10]  Kevin G. Coleman,et al.  Neural networks for bankruptcy prediction: the power to solve financial problems , 1991 .

[11]  Ramesh Sharda,et al.  A neural network model for bankruptcy prediction , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[12]  Youngohc Yoon,et al.  Applying Artificial Neural Networks to Investment Analysis , 1992 .

[13]  Claudio Gianotti,et al.  Economic and financial knowledge-based processing , 1990 .

[14]  Michael Galler,et al.  Analysis of Small-Business Financial Statements Using Neural Nets , 1995 .

[15]  E. Altman,et al.  ZETATM analysis A new model to identify bankruptcy risk of corporations , 1977 .

[16]  Pamela K. Coats,et al.  Recognizing Financial Distress Patterns Using a Neural Network Tool , 1993 .

[17]  Duane DeSieno,et al.  Trading Equity Index Futures With a Neural Network , 1992 .

[18]  Panayiotis Theodossiou Predicting Shifts in the Mean of a Multivariate Time Series Process: An Application in Predicting Business Failures , 1993 .

[19]  F. S. Wong,et al.  Fuzzy Neural Systems for Stock Selection , 1992 .