Using Inductive Learning to Predict Bankruptcy

An emerging trend in organizational computing is using information technology to learn decision knowledge from enterprise data. The primary contribution of this study is the presentation of a sound theory and a comprehensive technique for learning the decision model for predicting bankruptcy. The theory is based on the information contained in cash flow components, which is the foundation of valuation theory, and an analytical system that measures the amount of uncertainty in the cash flow information. The approach links a tree-based inductive learning system that relies on the concept of entropy, with an information system based on the cash flow of a firm. A test of the cash flow approach involves the cash flow components for a sample of 99 failed and 99 non-failed companies. The structural instability of cash flow components generated by an inductive learning system is a serious issue for financial analysts. However, this shortcoming is overcome by using a jackknife procedure to develop a global tree that identifies the most important cash flow components. The final global tree found only 3 cash flow components were needed to classify correctly 89% of the companies as either failed or non-failed. Only a few early studies achieved a higher level of predictive accuracy. The 3 significant cash flow components were dividends, net investment, and net operating cash flow. Using the same data, a probit statistical technique generated a 67.5% predictive accuracy. In summary, the inductive learning results indicate that cash flow components are not only a natural tool for explaining the bankruptcy process, but they provide a high level of predictive accuracy.

[1]  Richard S. Ruback,et al.  The Market for Corporate Control: The Scientific Evidence , 2002 .

[2]  James V. Hansen,et al.  Inducing rules for expert system development: an example using default and bankruptcy data , 1988 .

[3]  Paul Newbold,et al.  Funds Flow Components, Financial Ratios, and Bankruptcy , 1987 .

[4]  Mark I. Weinstein,et al.  The Behavior of the Common Stock of Bankrupt Firms , 1983 .

[5]  Charles P. Jones,et al.  An Analysis of Risk and Return Characteristics of Corporate Bankruptcy Using Capital Market Data , 1980 .

[6]  W. R. Garner.  Concept Learning: An Information- Processing Problem , 1964 .

[7]  Walter N. Torous,et al.  An Empirical Investigation of U.S. Firms in Reorganization , 1989, World Scientific Reference on Contingent Claims Analysis in Corporate Finance.

[8]  Michael J. Shaw,et al.  Inductive Learning Methods for Knowledge-Based Decision Support: A Comparative Analysis , 1990 .

[9]  Joseph E. Stiglitz,et al.  Some Aspects of the Pure Theory of Corporate Finance: Bankruptcies and Take-Overs: Reply , 1972 .

[10]  W. Beaver.  Financial Ratios As Predictors Of Failure , 1966 .

[11]  M. C. Jensen,et al.  The Takeover Controversy: Analysis and Evidence , 2003 .

[12]  M. Robert,et al.  THE INCREMENTAL INFORMATION CONTENT OF ACCRUAL VERSUS CASH FLOWS , 1987 .

[13]  C. Zavgren,et al.  The prediction of corporate failure: The state of the art , 1983 .

[14]  Brian L. Betker.  The Security Price Effects of Public Debt Defaults , 1998 .

[15]  John Mingers,et al.  An Empirical Comparison of Pruning Methods for Decision Tree Induction , 1989, Machine Learning.

[16]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[17]  Lemma W. Senbet,et al.  Bankruptcy and Agency Costs: Their Significance to the Theory of Optimal Capital Structure , 1988, Journal of Financial and Quantitative Analysis.

[18]  R. Kaplan,et al.  Statistical Models of Bond Ratings: A Methodological Inquiry , 1979 .

[19]  Chris Carter,et al.  Assessing Credit Card Applications Using Machine Learning , 1987, IEEE Expert.

[20]  F. Attneave.  Applications of information theory to psychology: A summary of basic concepts, methods, and results. , 1961 .

[21]  Judy Rayburn,et al.  THE ASSOCIATION OF OPERATING CASH FLOW AND ACCRUALS WITH SECURITY RETURNS , 1986 .

[22]  James A. Ohlson.  FINANCIAL RATIOS AND THE PROBABILISTIC PREDICTION OF BANKRUPTCY , 1980 .

[23]  Cornelius J. Casey,et al.  Using Operating Cash Flow Data to Predict Financial Distress: Some Extensions , 1985 .

[24]  Lemma W. Senbet,et al.  THE INSIGNIFICANCE OF BANKRUPTCY COSTS TO THE THEORY OF OPTIMAL CAPITAL STRUCTURE , 1978 .

[25]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[26]  Joshua Livnat,et al.  The incremental information content of cash-flow components , 1990 .

[27]  M. Zmijewski.  METHODOLOGICAL ISSUES RELATED TO THE ESTIMATION OF FINANCIAL DISTRESS PREDICTION MODELS , 1984 .

[28]  Jerold B. Warner.  Bankruptcy, absolute priority, and the pricing of risky debt claims , 1977 .

[29]  Paul Newbold,et al.  Profiles of Cash Flow Components , 1990 .

[30]  Michael C. Jensen,et al.  The market for corporate control , 1983 .

[31]  G P Wilson,et al.  THE RELATIVE INFORMATION-CONTENT OF ACCRUALS AND CASH FLOWS - COMBINED EVIDENCE AT THE EARNINGS ANNOUNCEMENT AND ANNUAL-REPORT RELEASE DATE , 1986 .

[32]  W. R. Lane,et al.  An application of the cox proportional hazards model to bank failure , 1986 .

[33]  James H. Scott.  The probability of bankruptcy: A comparison of empirical predictions and theoretical models , 1981 .

[34]  Annette B. Poulsen,et al.  Free Cash Flow and Stockholder Gains in Going Private Transactions , 1989 .

[35]  M. White,et al.  Bankruptcy Costs and the New Bankruptcy Code , 1983 .

[36]  M. Shaw,et al.  Using an Expert System with Inductive Learning to Evaluate Business Loans , 1988 .

[37]  P G Wilson,et al.  THE INCREMENTAL INFORMATION CONTENT OF THE ACCRUAL AND FUNDS COMPONENTS OF EARNINGS AFTER CONTROLLING FOR EARNINGS , 1987 .

[38]  W. Shaw,et al.  Investing in Bankrupt Firms , 1988 .

[39]  Rupert G. Miller.  Beyond ANOVA, basics of applied statistics , 1987 .

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

[41]  Claude E. Shannon,et al.  Prediction and Entropy of Printed English , 1951 .

[42]  Michael J. Shaw,et al.  Inductive Learning for International Financial Analysis: A Layered Approach , 1993, J. Manag. Inf. Syst..

[43]  Paul Newbold,et al.  Predicting Bankruptcy: If Cash Flow’s Not the Bottom Line, What Is? , 1985 .

[44]  Paul Newbold,et al.  PREDICTING INDUSTRIAL BOND RATINGS WITH A PROBIT MODEL AND FUNDS FLOW COMPONENTS , 1988 .

[45]  Michael J. Shaw,et al.  Applying inductive learning to enhance knowledge-based expert systems , 1987, Decis. Support Syst..

[46]  George Foster,et al.  Corporate Financial-Reporting - A Methodological Review Of Empirical-Research , 1982 .

[47]  Merton H. Miller,et al.  Dividend Policy under Asymmetric Information , 1985 .

[48]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

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

[50]  Paul Newbold,et al.  CLASSIFYING BANKRUPT FIRMS WITH FUNDS FLOW COMPONENTS , 1985 .

[51]  V. Bernard,et al.  THE NATURE AND AMOUNT OF INFORMATION IN CASH FLOWS AND ACCRUALS , 1989 .