A Nonlinear Approach to Assess the Risk–Reward Ratio Using the Machine Learning Technique

  • Pasquale MerellaEmail author
  • Roberto Schiesari


The objective of our work is to assess the reliability of the machine learning techniques estimating the default probabilities. In our work, we followed an alternative nonlinear separation method known as the Support Vector Machine (SVM) for the default risk analysis. We did not need any parameter restrictions or prior assumptions in our estimates. We analysed more than 42,000 Italian companies, using the AIDA dataset spanning the years 2011 through to 2016, proposing an SVM model based on the performance measures such as ratios of leverage, liquidity and activity. The results of our work point out that using nonlinear techniques for predicting bankruptcy allows to achieve better performances than traditional statistical ones and, moreover, shows the important predictors to estimate default probabilities.


  1. Abdou, H. A., & Pointon, J. (2009). Credit scoring and decision-making in Egyptian public sector banks. International Journal of Managerial Finance, 5(4), 391–406.CrossRefGoogle Scholar
  2. Aghion, P., & Bolton, P. (1992). An “incomplete contracts” approach to financial contracting. Review of Economic Studies, 59(3), 473–494.CrossRefGoogle Scholar
  3. Altman, E. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, 23(4), 589–611. CrossRefGoogle Scholar
  4. Altman, E., Haldeman, R., & Narayanan, P. (1977). Zeta analysis: A new model to identify bankruptcy risk of corporations. Journal of Banking and Finance, 7, 29–54. Google Scholar
  5. Altman, E. I., & Kao, D. R. (1992). Rating drift in high-yield bonds. The Journal of Fixed Income Spring, 1(4), 15–20.CrossRefGoogle Scholar
  6. Ayer, M., Brunk H. D., Ewing, G. M., Reid, W. T., & Silverman, E. (1955). An empirical distribution function for sampling with incomplete information. The Annals of Mathematical Statistics, 26, 641–647.Google Scholar
  7. Aziz, A., Emanuel, D. C., & Lawson, G. H. (1988). Bankruptcy prediction—An investigation of cash flow based models. Journal of Management Studies, 25(5), 419–437.Google Scholar
  8. Back, B., Laitinen, T., & Sere, K. (1994). Neural networks and bankruptcy prediction. Paper presented at the 17th Annual Congress of the European Accounting Association, Venice, Italy, 1994. Abstract in Collected Abstracts of the 17th Annual Congress of the European Accounting Association 116.Google Scholar
  9. Back, B., Laitinen, T., Sere, K., & Wezel, M. (1996). Choosing bankruptcy predictors using discriminant analysis, logit analysis, and genetic algorithms. Technical Report 40, TUCS Research Group.Google Scholar
  10. Bailey, M. (2004). Consumer credit quality: Underwriting, scoring, fraud prevention and collections. Kingswood and Bristol: White Box Publishing.Google Scholar
  11. Barlow, R. E., Bartholomew, J. M., Bremmer, J. M., & Brunk, H. D. (1972). Statistical inference under order restrictions. New York, NY: Wiley.Google Scholar
  12. Beaver, W. (1966). Financial ratios as predictors of failures empirical research in accounting: Selected studies. Journal of Accounting Research, 7, 71–111. Supplement to vol. 5. CrossRefGoogle Scholar
  13. Beaver, W. (1967). Financial ratios predictors of failure, empirical research in accounting: Selected studies 1966. Journal of Accounting Research, 4, 71–111.Google Scholar
  14. Berger, A. N., & Frame, W. S. (2007). Small business credit scoring and credit availability. Journal of Small Business Management, 47, 5–22.CrossRefGoogle Scholar
  15. Bierman, H., & Hausman, W. H. (1970). The credit granting decision. Management Science, 16(8), 519–532.CrossRefGoogle Scholar
  16. Bilderbeek, J. (1979, May). An empirical study of the predictive ability of financial ratios in the Netherlands. Zeitschrift fur Betriebswirtsthaft, 49, 388–407. Google Scholar
  17. Black, F., Jensen, M. C., & Scholes, M. (1972). The capital asset pricing model: Some empirical tests (pp. 79–121). Studies in the Theory of Capital Markets. New York, NY: Praeger.Google Scholar
  18. Blum, M. (1974). Failing company discriminant analysis. Journal of Accounting Research, 12(1), 1–25.CrossRefGoogle Scholar
  19. Breeden, D. T. (1979). An intertemporal asset pricing model with stochastic consumption and investment opportunities. Journal of Financial Economics, 7, 265–296.CrossRefGoogle Scholar
  20. Carty, L., & Fons, J. (1994, June). Measuring changes in corporate credit quality. Journal of Fixed Income, 4, 27–41.Google Scholar
  21. Chakrabarti, B., & Varadachari, R. (2004). Quantitative methods for default probability estimation—A first step towards Basel II. i-flex solutions.Google Scholar
  22. Chandler, G. G., & Coffman, J. Y. (1979). A comparative analysis of empirical vs. judgemental credit valuation. The Journal of Retail Banking, 1(2), 15–26.Google Scholar
  23. Charitou, A., & Trigeorgis, L. (2002, July 4–6). Option-based bankruptcy prediction. Paper presented at 6th Annual Real Options Conference, Paphos, Cyprus, pp. 1–25.Google Scholar
  24. Collins, R., & Green, R. (1982). Statistical methods for bankruptcy prediction. Journal of Economics and Business, 34(4), 349–354.CrossRefGoogle Scholar
  25. Crook, J. N. (1996). Credit scoring: An overview (Working Paper Series No. 96/13). British Association, Festival of Science. University of Birmingham, The University of Edinburgh.Google Scholar
  26. Deakin, E. B. (1972). A discriminant analysis of predictors of business failure. Journal of Accounting Research, 10(March), 167–179. CrossRefGoogle Scholar
  27. Deng, N. Y., & Tian, Y. J. (2004). New methods in data mining: Support vector machine. Beijing: Science Press. Google Scholar
  28. Edmister, R. (1972). An empirical test of financial ratio analysis for small business failure prediction. Journal of Financial and Quantitative Analysis, 7, 1477–1493. CrossRefGoogle Scholar
  29. Engelmann, B., Hayden, E., & Tasche, D. (2003). Testing rating accuracy. Risk, 16, 82–86.Google Scholar
  30. Efron, B., & Tibshirani, R. (1993). An introduction to the bootstrap. New York, NY: Chapman & Hall.CrossRefGoogle Scholar
  31. Falkenstein, E., Boral, A., & Carty, L. (2000). Riskcalc for private companies: Moody’s default model. As published in Global Credit Research.Google Scholar
  32. Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, 33(1), 3–56.CrossRefGoogle Scholar
  33. Fama, E. F., & French, K. R. (1996). The capm is wanted, dead or alive. Journal of Finance, 51(5), 1947–1958.CrossRefGoogle Scholar
  34. Fama, E. F., & MacBeth, J. D. (1973). Risk, return, and equilibrium: Empirical tests. Journal of Political Economy, 81(3), 607–636.CrossRefGoogle Scholar
  35. Fitzpatrick, P. (1932). A comparison of the ratios of successful industrial enterprises with those of failed companies. Certified Public Accountant, 6, 727–731.Google Scholar
  36. Franke, G., Stapleton, R. C., & Subrahmanyam, M. G. (1999). When are options overpriced? The black-scholes model and alternative characterisations of the pricing kernel. European Finance Review, 3, 79–102.CrossRefGoogle Scholar
  37. Gentry, J. A., Newbold, P., & Whitford, D. T. (1985). Classifying bankrupt firms with funds flow components. Journal of Accounting Research, 23(1), 146–160.CrossRefGoogle Scholar
  38. Gombola, M., Haskins, M., Ketz, J., & Williams, D. (1987). Cash flow in bankruptcy prediction. Financial Management, 16(Winter), 55–65. Google Scholar
  39. Gupton, G. M., Finger, C. C., & Bhatia, M. (1997). CreditMetrics – Technical Document. Morgan Guaranty Trust Company.Google Scholar
  40. Hand, D. J., & Henley, W. E. (1997). Statistical classification methods in consumer credit scoring: A review. Journal of the Royal Statistical Society, 160(3), 523–541.CrossRefGoogle Scholar
  41. Härdle, W. Moro, R.A. and Schäfer, D. (2005). Predicting bankruptcy with support vector machines. In Statistical tools for finance and insurance. Berlin: Springer Verlag.Google Scholar
  42. Härdle, W., Moro, R. A., & Schäfer, D. (2007). Graphical data representation in bankruptcy analysis. In Handbook for data visualization. Berlin: Springer Verlag.Google Scholar
  43. Härdle, W., Müller, M., Sperlich, S., & Werwatz, A. (2004). Nonparametric and semiparametric models. Heidelberg: Springer.Google Scholar
  44. Härdle, W., & Simar, L. (2003). Applied multivariate statistical analysis. Berlin: Springer.Google Scholar
  45. Haykin, S. (1999). Neural networks: A comprehensive foundations. Upper Saddle River, NJ: Prentice Hall. Google Scholar
  46. He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21, 1263–1284.Google Scholar
  47. Herrity, J. V., Keenan, S. C., Sobehart, J. R., Carty, L. V., & Falkenstein, E. G. (1999). Measuring private firm default risk. Special Comment, Moody’s Investors Service.Google Scholar
  48. Horowitz, J. L. (2001). The bootstrap (Vol. 5). Amsterdam: Elsevier Science B.V. Google Scholar
  49. Keasey, K., & Watson, R. (1991). Financial distress models: A review of their usefulness. British Journal of Management, 2(2), 89–102.Google Scholar
  50. Keenan, S. C., & Sobehart, J. R. (1999). Performance measures for credit risk models (Research Report #1-10-10-99). Moody’s Risk Management Services.Google Scholar
  51. Keerthi, S. S., & Lin, C. J. (2003). Asymptotic behaviors of support vector machines with gaussian kernel. In Neural Computation, 15, 1667–1689.Google Scholar
  52. Khandani, B., Lozano, M., & Carty, L. (2001). Moody’s riskcalc for private companies: The german model. Rating Methodology, Moody’s Investors Service.Google Scholar
  53. Lennox, C. (1999). Identifying failing companies: A re-evaluation of the logit, probit and da approaches. Journal of Economics and Business, 51, 347–364.CrossRefGoogle Scholar
  54. Lintner, J. (1965). The valuation of risk assets and the selection of risky investments in stock portfolios and capital budgets. Review of Economics and Statistics, 47(1), 13–37.CrossRefGoogle Scholar
  55. Lo, A. W. (1986). Logit versus discriminant analysis: A specification test and application to corporate bankruptcies. Journal of Econometrics, 31(2), 151–178.CrossRefGoogle Scholar
  56. Lussier, R. N. (1995). A non-financial business success versus failure prediction model for young firms. Journal of Small Business Management, 33(1), 8–20.Google Scholar
  57. Mammen, E. (1991). Estimating a smooth monotone regression function. Annals of Statistics, 19, 724–740.CrossRefGoogle Scholar
  58. Markowitz, H. (1959). Portfolio selection: Efficient diversification of investments (Cowles Foundation Monograph No. 16). New York, NY: Wiley.Google Scholar
  59. Mayers, D. (1972). Non-marketable assets and capital market equilibrium under uncertainty. In Studies in the theory of capital markets (pp. 223–247). New York: Praeger. Google Scholar
  60. Merton, R. C. (1973). An intertemporal capital asset pricing model. Econometrica, 41(5), 867–887.CrossRefGoogle Scholar
  61. Merton, R. C. (1974). On the pricing of corporate debt: The risk structure of interest rates. Journal of Finance, 29, 449–470.Google Scholar
  62. Merwin, C. (1942). Financing small corporations in five manufacturing industries, 1926–36. New York: National Bureau of Economic Research. Google Scholar
  63. Micha, B. (1984). Analysis of business failures in France. Journal of Banking & Finance, 8, 281–291.CrossRefGoogle Scholar
  64. Mossman, Ch. E., Bell, G. G., Swartz, L. M., & Turtle, H. (1998). An empirical comparison of bankruptcy models. The Financial Review, 33(2), 35–54.Google Scholar
  65. Myers, S. (1977). Determinants of corporate borrowing. Journal of Financial Economics, 5(2), 147–175.CrossRefGoogle Scholar
  66. Ohlson, J. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research, 18, 109–131. CrossRefGoogle Scholar
  67. Ooghe, H., Joos, P., & De Bourdeaudhuij, C. (1995). Financial distress models in Belgium: The results of a decade of empirical research. International Journal of Accounting, 30, 245–274.Google Scholar
  68. Platt, H., Platt, M., & Pedersen, J. (1994). Bankruptcy discrimination with real variables. Journal of Business, Finance and Accounting, 21(4), 491–510.CrossRefGoogle Scholar
  69. Platt, H. D., & Platt, M. B. (1990). Development of a class of stable predictive variables: The case of bankruptcy prediction. Journal of Business Finance & Accounting, 17(1), 31–51.CrossRefGoogle Scholar
  70. Ramser, J., & Foster, L. (1931). A demonstration of ratio analysis (Bulletin No. 40). Urbana: Bureau of Business Research, University of Illinois.Google Scholar
  71. Roll, R. (1997). A critique of the asset pricing theory’s tests. Part I: On past and potential testability of the theory. Journal of Financial Economics, 4(2), 129–176.CrossRefGoogle Scholar
  72. Ross, S. A. (1976). The arbitrage theory of capital asset pricing. Journal of Economic Theory, 13(3), 341–360.CrossRefGoogle Scholar
  73. Serrano, C., Martin, B., & Gallizo, J. L. (1993, April 28–30). Artificial neural networks in financial statement analysis: Ratios versus accounting data. Technical report, paper presented at the 16th Annual Congress of the European Accounting Association, Turku, Finland.Google Scholar
  74. Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. Journal of Finance, 19(3), 425–442.Google Scholar
  75. Sobehart, J., Keenan, S., & Stein, R. (2001). Benchmarking quantitative default risk models: A validation methodology. Algo Research Quarterly, 4, 55–69.Google Scholar
  76. Taffler, R. J., & Tisshaw H. (1977). Going, going, gone—Four factors which predict. Accountancy, 88(March), 50–54.Google Scholar
  77. Thomas, L. C. (2000). A survey of credit and behavioural scoring: Forecasting financial risk of lending to consumers. International Journal of Forecasting, 16(2), 149–172.CrossRefGoogle Scholar
  78. Tikhonov, A. N. (1963). On solving ill-posed problem and method regularization. Doklady Akademii Nauk USSR, 153, 501–504.Google Scholar
  79. Tikhonov, A. N., & Arsenin, V. Y. (1977). Solution of ill-posed problems. Washington, DC: W. H. Winston.Google Scholar
  80. Vapnik, V. (1979). Estimation of dependencies based on empirical data. Moscow: Nauka.Google Scholar
  81. Vapnik, V. (1995). The nature of statistical learning theory. New York, NY: Springer.CrossRefGoogle Scholar
  82. Vapnik, V. (1997). Statistical learning theory. New York, NY: Wiley.Google Scholar
  83. Wilson, R. L., & Sharda, R. (1994). Bankruptcy prediction using neural networks. Decision Support Systems, 11, 545–557.CrossRefGoogle Scholar
  84. Winakor, A., & Smith, R. (1935). Changes in the financial structure of unsuccessful industrial corporations (Bulletin No. 51). Urbana: Bureau of Business Research, University of Illinois.Google Scholar

Copyright information

© The Author(s) 2019

Authors and Affiliations

  1. 1.Green Arrow Capital SGRMilanItaly
  2. 2.Department of ManagementUniversity of TurinTurinItaly

Personalised recommendations