Skip to main content
SpringerLink
Log in

Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers

  • Published:
Journal of Economics and Finance Aims and scope Submit manuscript

Abstract

Past studies have documented the failure of the Insurance Regulatory Information System (IRIS) to provide adequate warning of insurer financial distress or insolvency. As a result, scholars have examined alternative parametric and non-parametric models to predict insurer insolvency. This study uses a neural network, a non-parametric alternative to past techniques, and shows how this methodology predicts insurer insolvency more effectively than parametric models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Altman, Edward I., Robert B. Avery, Robert A. Eisenbeis, andJoseph F. Sinkey.Application of Classification Techniques in Business, Banking, and Finance. Greenwich, Connecticut: JAI Press, 1981.

    Google Scholar 

  • Altman, Edward I. “Financial Ratios, Discriminant Analysis, and the Prediction of Corporate Bankruptcy.”Journal of Finance 23, no. 4 (September 1968): 589–609.

    Article  Google Scholar 

  • Ambrose, Jan Mills andAllen J. Seward. “Best's Rating, Financial Ratios and Prior Probabilities in Insolvency Prediction.”The Journal of Risk and Insurance 55, no. 2 (July 1988): 229–244.

    Article  Google Scholar 

  • American Council of Life Insurance.1992 Life Insurance Fact Book, Washington, D.C. 1992.

  • BarNiv, Ran, andJames B. McDonald. “Identifying Financial Distress in the Insurance Industry: A Synthesis of Methodological and Empirical Issues.”The Journal of Risk and Insurance 59, no. 4 (December 1992): 543–574.

    Article  Google Scholar 

  • BarNiv, Ran, andRobert A. Hershbarger. “Classifying Financial Distress in the Life Insurance Industry.”The Journal of Risk and Insurance 57, no. 1 (Spring 1990): 110–136.

    Article  Google Scholar 

  • BarNiv, Ran. andAdi Raveh. “Identifying Financial Distress: A New Non-Parametric Approach.”Journal of Business Finance and Accounting 16, no. 3 (Summer 1989): 361–383.

    Google Scholar 

  • Barrese, James. “Assessing the Financial Condition of Insurers.”CPCU Journal 43, no. 1 (March 1990): 37–46.

    Google Scholar 

  • Berkson, Joseph. “Maximum Likelihood and Miximum Chi-Square Estimates of the Logistic Function.”Journal of the American Statistical Association 50, no. 269 (March 1955): 130–162.

    Article  Google Scholar 

  • A. M. Best Company.Best's Trend Report-Life and Health Edition. Oldwick, N.J.: A.M. Best Company, 1994.

    Google Scholar 

  • Brockett, Patrick L. William W. Copper, Linda L. Golden, andUtai Pitaktong. “A Neural Network Method for Obtaining an Early Warning of Insurer Insolvency.”Journal of Risk and Insurance 61, no. 3 (September 1994): 402–424.

    Article  Google Scholar 

  • Caudill, Maureen. “Using Neural Nets: Representing Knowledge.”AI Expert 4, no. 12 (December 1989): 34–41.

    Google Scholar 

  • Christine, Brian. “On Raters, Ratings, and New Legislation.”Risk Management 39, no. 8 (August 1992): 63.

    Google Scholar 

  • Deakin, Edward B. “Distributions of Financial Accounting Ratios: Some Empirical Evidence.”Accounting Review 51, no. 1 (January 1976): 90–96.

    Google Scholar 

  • DeSilets, Lenore., Bruce Golden, Qiwen Wang, andRan Kumar. “Predicting Salinity in the Chesapeake Bay Using Back Propagation.”Computers and Operations Research 19, no. 3 (April 1992): 277–285.

    Article  Google Scholar 

  • Ebell, Mark H. “Artificial Neural Networks for Predicting Failure to Survive Following In-Hospital Cardiopulmonary Resuscitation.”The Journal of Family Practice 36, no. 3 (March 1993): 297–303.

    Google Scholar 

  • Efron, Bradley. “Regression and ANOVA with Zero-One Data: Measures of Residual Variation.”Journal of the American Statistical Association 73, no. 361 (March 1978): 113–121.

    Article  Google Scholar 

  • Fisher, R. A. “The Use of Multiple Measurements in Taxonomic Problems.”Annals of Eugenics 7, no. 2 (September 1936): 179–188.

    Google Scholar 

  • Frydman, Halina, Edward I. Altman, andDuen Li Kao. “Introducing Recursive Partitioning for Financial Classification: The Case of Financial Distress.”Journal of Finance 40, no. 1 (March 1985): 269–291.

    Article  Google Scholar 

  • Harrington, Scott E. andJack M. Nelson. “A Regression-Based Methodology for Solvency Surveillance in the Property-Liability Insurance Industry.”Journal of Risk and Insurance 53, no. 4 (December 1986): 583–606.

    Article  Google Scholar 

  • Hecht-Nielsen, Robert.Neurocomputing. New York: Addison-Wesley, 1990.

    Google Scholar 

  • Hecht-Nielsen, Robert. “Kolmogorov's Mapping Neural Network Existence Theorem.” IEEE First International Conference on Neural Networks, 1 (1987): 11–14.

    Google Scholar 

  • Hershbarger Robert A. andRonald Miller. “The NAIC Information System and the Use of Economic Indicators in Predicting Insolvencies.”The Journal of Insurance Issues and Practices 9, no. 2 (June 1986): 21–43.

    Google Scholar 

  • Lachenbruch, Peter A., Cheryl Sneeringer, andLawrence T. Revo. “Robustness of the Linear and Quadratic Discriminant Function to Certain Types of Non-normality.”Communication In Statistics 1, no. 1 (1973): pp. 39–56.

    Article  Google Scholar 

  • Lachenbruch, Peter A. “An Almost Unbiased Method of Obtaining Confidence Intervals for the Probability of Misclassification in Discriminant Analysis.”Biometrics 23, no. 4 (December 1967): 639–645.

    Article  Google Scholar 

  • Lippmann, R.P. “An Introduction to Computing with Neural Nets.” IEEE, ASSP, 4, (April 1987): 4–22.

    Article  Google Scholar 

  • Lo, Andrew W. “Logit Versus Discriminant Analysis: A Specification Test and Application to Corporate Bankruptcies.”Journal of Econometrics 31, no. 2 (March 1986): 151–178.

    Article  Google Scholar 

  • Marose, Robert A. “A Financial Neural-Network Application.”AI Expert 5, no. 5 (May 1990): 50–53.

    Google Scholar 

  • Maren, Alianna. J., Dan Jones, andStanley Franklin.Handbook of Neural Computing Applications. San Diego, CA: Academic Press, 1990.

    Google Scholar 

  • McFadden, Daniel. “A Comment on Discriminant Analysis Versus Logit Analysis.”Annals of Economic and Social Measurement 5, no. 4 (1976): 511–523.

    Google Scholar 

  • Messier, William F., andJames V. Hansen. “Inducing Rules for Expert System Development: An Example Using Default and Bankruptcy Data.”Management Science 34, no. 12 (December 1988): 1403–15.

    Google Scholar 

  • National Association of Insurance Commissioners.NAIC-IRIS Tests, Using the NAIC Insurance Regulatory Information System, Life and Health Edition, Madison, WI: NAIC, 1986.

    Google Scholar 

  • Ono, Takahi. “Chaos Engineering Coming in 1993.”Japan Times Weekly International Edition 33, no. 4 (January 1993): pp. 16.

    Google Scholar 

  • Pao, Yoh-Han.Adaptive Pattern Recognition and Neural Networks. Reading, MA: Addison-Wesley, 1989.

    Google Scholar 

  • Pinches, George E. andJames S. Trieschmann. “Discriminant Analysis, Classification Results and Financially Distressed P-L Insurers.”The Journal of Risk and Insurance 44, no. 2 (June 1977): 289–298.

    Article  Google Scholar 

  • Press, S. James andSandra Wilson. “Choosing Between Logistic Regression and Discriminant Analysis.”Journal of American Statistical Association 73, no.364 (December 1978): 699–705.

    Article  Google Scholar 

  • Radcliffe, Steve. “Where Have All the Margins Gone.”Best's Review, Life/Health Insurance Edition (April 1982): 10–15.

  • Rumelhart, D.E., G.E. Hinton andR.J. Williams. “Learning Internal Representations by Error Propagation.” inParallel Distributed Processing Exploration in the Microstructure of Cognition, ed. D.E. Rumelhart and J.L. McClelland, 318–362. Cambridge, MA: MIT Press, 1986.

    Google Scholar 

  • Soulie, F., P. Gallinari, Y. Cun, andS. Thiria. “Evaluation of Network Architectures on Test Learning Tasks.”IEEE First International Conference on Neural Networks, II (1990): 653–660.

    Google Scholar 

  • Thornton, John H. andJoseph W. Meador. “Comments on the Validity of the NAIC Early Warning System for Predicting Failures Among Property and Liability Insurance Companies.”CPCU Annals 30 (September 1977): 191–211.

    Google Scholar 

  • Vogel, Gloria L. “An Analyst's View of Insurance Insolvency.”Journal of the American Society of CLU and ChFC 46, no. 3 (May 1992): 52–58.

    Google Scholar 

  • Wann, M. T. Hediger andN. Greenbaum. “The Influence of Training Sets on Generalization in Feed-Forward Neural Networks.”IEEE First International Joint Conference on Neural Networks 3 (1990): 137–142.

    Article  Google Scholar 

  • White, Halbert. “Neural Network Learning and Statistics.”AI Expert 4, no. 12 (December 1989): 48–52.

    Google Scholar 

  • Widrow, Bernard, and Marcian E. Hoff. “Adaptive Switching Circuits.” 96–104, New York: Institute of Radio Engineers, Western Electronic Shoe and Conference, Convention Record, 1960.

  • Yoon, Youngohc, George Swales, Jr. andThomas M. Margavio. “A Comparison of Discriminant Analysis Versus Artificial Neural Networks.”Journal of Operational Research Society 44, no. 1 (January 1993): 51–60.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Creighton University, 68178-0130, Omaha, NE

    Ernest Preston Goss & Harish Ramchandani

Authors
  1. Ernest Preston Goss
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Harish Ramchandani
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Goss, E.P., Ramchandani, H. Comparing classification accuracy of neural networks, binary logit regression and discriminant analysis for insolvency prediction of life insurers. J Econ Finan 19, 1–18 (1995). https://doi.org/10.1007/BF02920611

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02920611

Keywords

Search

Navigation