Advertisement

Evolutionary Learning of Technical Trading Rules without Data-Mining Bias

  • Alexandros Agapitos
  • Michael O’Neill
  • Anthony Brabazon
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6238)

Abstract

In this paper we investigate the profitability of evolved technical trading rules when controlling for data-mining bias. For the first time in the evolutionary computation literature, a comprehensive test for a rule’s statistical significance using Hansen’s Superior Predictive Ability is explicitly taken into account in the fitness function, and multi-objective evolutionary optimisation is employed to drive the search towards individual rules with better generalisation abilities. Empirical results on a spot foreign-exchange market index suggest that increased out-of-sample performance can be obtained after accounting for data-mining bias effects in a multi-objective fitness function, as compared to a single-criterion fitness measure that considers solely the average return.

Keywords

Daily Return Trading Rule Evolutionary Search Evolutionary Learn Technical Indicator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aronson, D.: Evidence-Based Technical Analysis. John Wiley and Sons, Inc., Chichester (2007)Google Scholar
  2. 2.
    Pardo, R.: Design, testing and optimisation of trading systems. John Wiley and Sons, Inc., Chichester (1992)Google Scholar
  3. 3.
    O’Neill, M., Brabazon, A., Ryan, C., Collins, J.J.: Evolving market index trading rules using grammatical evolution. In: Boers, E.J.W., Gottlieb, J., Lanzi, P.L., Smith, R.E., Cagnoni, S., Hart, E., Raidl, G.R., Tijink, H. (eds.) EvoIASP 2001, EvoWorkshops 2001, EvoFlight 2001, EvoSTIM 2001, EvoCOP 2001, and EvoLearn 2001. LNCS, vol. 2037, pp. 343–352. Springer, Heidelberg (2001)Google Scholar
  4. 4.
    Thomas, J.D., Sycara, K.: The importance of simplicity and validation in genetic programming for data mining in financial data. In: Freitas, A.A. (ed.) Data Mining with Evolutionary Algorithms: Research Directions, Orlando, Florida, Technical Report WS-99-06, July 18, pp. 7–11. AAAI Press, Menlo Park (1999)Google Scholar
  5. 5.
    Iba, H., De Garis, H., Sato, T.: Genetic programming using a minimum description length principle. In: Advances in Genetic Programming, pp. 265–284. MIT Press, Cambridge (1994)Google Scholar
  6. 6.
    Breiman, L., Breiman, L.: Bagging predictors. Machine Learning, 123–140 (1996)Google Scholar
  7. 7.
    O’Neill, M., Ryan, C.: Grammatical Evolution: Evolutionary Automatic Programming in a Arbitrary Language. Genetic programming, vol. 4. Kluwer Academic Publishers, Dordrecht (2003)zbMATHGoogle Scholar
  8. 8.
    White, H.: A reality check for data snooping. Econometrica 68(5), 1097–1126 (2000)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Hansen, P.R.: A test for superior predictive ability. Journal of Business & Economic Statistics 23, 365–380 (2005)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Romano, J., Politis, D.: The stationary bootstrap. Journal of American Statistical Association 89(428), 1303–1313 (1994)MathSciNetzbMATHCrossRefGoogle Scholar
  11. 11.
    Kaufman, P.: New Trading Systems and Methods, 4th edn. Wiley, Chichester (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alexandros Agapitos
    • 1
  • Michael O’Neill
    • 1
  • Anthony Brabazon
    • 1
  1. 1.Financial Mathematics and Computation Research Cluster, Natural Computing Research and Applications Group, Complex and Adaptive Systems LaboratoryUniversity College DublinIreland

Personalised recommendations