Adapting support vector machine methods for horserace odds prediction



The methodology of Support Vector Machine Methods is adapted in a straightforward manner to enable the analysis of stratified outcomes such as horseracing results. As the strength of the Support Vector Machine approach lies in its apparent ability to produce generalisable models when the dimensionality of the inputs is large relative to the the number of observations, such a methodology would appear to be particularly appropriate in the horseracing context, where often the number of input variables deemed as being potentially relevant can be difficult to reconcile with the scarcity of relevant race results. The methods are applied to a relatively small (200 races in-sample) sample of Australian racing data and tested on 100 races out-of-sample with promising results, especially considering the relatively large number (12) of input variables used.


Computational Finance Wagering Markets 


  1. Benter, W. (1994).“Computer Based Horserace Handicapping and Wagering Systems: A Report.” In L. Hausch and Ziemba (eds.), Efficiency of Racetrack Betting Markets. San Diego, CA: Academic Press, pp. 183–198.Google Scholar
  2. Benter, W. (2003). “Advances in the Mathematical Modeling of Horse Race Outcomes.” 12th International Conference on Gambling and Risk-Taking, Vancouver, BC, Canada (May 2003) (Proceedings).Google Scholar
  3. Bolton, R., and R.G. Chapman. (1986). “Searching for Positive Returns at the Track: A Multinomial Logit Model for Handicapping Horseraces.” Management Science, 32(8), 1040–1060.CrossRefGoogle Scholar
  4. Breiman, L. (1961).“Optimal Gambling Systems for Favorable Games.” Proceedings of the 4th Berkeley Symposium on Mathematics Statistics and Probability, 1, 63–68.Google Scholar
  5. Edelman, D. (2000). “On the Financial Value of Information,” Annals of Operations Research, 100, 123–132.CrossRefGoogle Scholar
  6. Edelman, D. (2001). The Compleat Horseplayer. Sydney: De Mare Consultants.Google Scholar
  7. Hausch, et al. (1994). In L. Hausch and Ziemba (eds.), Efficiency of Racetrack Betting Markets, Ch. 4. San Diego, CA: Academic Press.Google Scholar
  8. Kelly, J. (1956). “A New Interpretation of the Information Rate.” Bell System Technology Journal, 35, 917–926.Google Scholar
  9. Maclean, L.C., W.T. Ziemba, and G. Blazenko. (1994). “Growth versus Security in Dynamic Investment Analysis.” L. Hausch and Ziemba (eds.), Efficiency of Racetrack Betting Markets. San Diego, CA: Academic Press, pp. 127–150.Google Scholar
  10. Markowitz, H.M. (1952). “Portfolio Selection.” Journal of Finance, 7, 77–91.CrossRefGoogle Scholar
  11. Platt, J. (1998). “Sequential Minimal Optimisation: A Fast Algorithm for Training Support Vector Machines.” Microsoft Research Technical Report MSR-TR-98-14.Google Scholar
  12. Platt, J. (1999). “Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods.” In A. Smola, P. Bartlett, B. Schœlkopf, and D. Schuurmans (eds.), Advances in Large Margin Classifiers. MIT Press.Google Scholar
  13. Scott, D. (1985). Winning More. Sydney: Horwitz/Grahame.Google Scholar
  14. Sharpe, W. (1994). “The Sharpe Ratio.” Journal of Portfolio Management, 21(1), 49–58.CrossRefGoogle Scholar
  15. Shin, H.S. (1991). “Optimal Betting Odds Against Insider Traders.” Economic Journal, 101, 1179–1185.CrossRefGoogle Scholar
  16. Shin, H.S. (1993). “Measuring the Incidence of Insider Trading in a Market for State-Contingent Claims.” Economic Journal, 103, 1141–1153.CrossRefGoogle Scholar
  17. Vapnik, V. (2001). The Nature of Statistical Learning Theory, 2nd ed. New York: Springer.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  1. 1.Banking & Finance UnitUniversity CollegeCo. DublinIreland

Personalised recommendations