On the investigation of hyper-heuristics on a financial forecasting problem

  • Michael Kampouridis
  • Abdullah Alsheddy
  • Edward Tsang
Article

Abstract

Financial forecasting is a really important area in computational finance, with numerous works in the literature. This importance can be reflected in the literature by the continuous development of new algorithms. Hyper-heuristics have been successfully used in the past for a number of search and optimization problems, and have shown very promising results. To the best of our knowledge, they have not been used for financial forecasting. In this paper we present pioneer work, where we use different hyper-heuristics frameworks to investigate whether we can improve the performance of a financial forecasting tool called EDDIE 8. EDDIE 8 allows the GP (Genetic Programming) to search in the search space of indicators for solutions, instead of using pre-specified ones; as a result, its search area has dramatically increased and sometimes solutions can be missed due to ineffective search. We apply 14 different low-level heuristics to EDDIE 8, to 30 different datasets, and examine their effect to the algorithm’s performance. We then select the most prominent heuristics and combine them into three different hyper-heuristics frameworks. Results show that all three frameworks are competitive, and are able to show significantly improved results, especially in the case of best results. Lastly, analysis on the weights of the heuristics shows that there can be a constant swinging among some of the low-level heuristics, which denotes that the hyper-heuristics frameworks are able to ‘know’ the appropriate time to switch from one heuristic to the other, based on their effectiveness.

Keywords

Hyper-heuristics Genetic programming Financial forecasting 

Mathematics Subject Classifications (2010)

68T20 91B28 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agapitos, A., O’Neill, M., Brabazon, A.: Evolutionary learning of technical trading rules without data-mining bias. In: Schaefer, R., Cotta, C. Kołodziej, J. Rudolph, G. (eds.) Parallel Problem Solving from Nature—PPSN XI, Lecture Notes in Computer Science, vol. 6238, pp. 294–303. Springer (2010)Google Scholar
  2. 2.
    Allen, F., Karjalainen, R.: Using genetic algorithms to find technical trading rules. J. Financ. Econ. 51, 245–271 (1999)CrossRefGoogle Scholar
  3. 3.
    Austin, M., Bates, G., Dempster, M., Leemans, V., Williams, S.: Adaptive systems for foreign exchange trading. Quantitative Finance 4(4), 37–45 (2004)CrossRefGoogle Scholar
  4. 4.
    Backus, J.: The syntax and semantics of the proposed international algebraic language of Zurich. In: International Conference on Information Processing, pp. 125–132. UNESCO (1959)Google Scholar
  5. 5.
    Baluja, S.: Population-based incremental learning: a method for integrating genetic search based function optimisation and competitive learning. Technical Report, Carnegie Mellon University (1994)Google Scholar
  6. 6.
    Bernal-Urbina, M., Flores-Méndez, A.: Time series forecasting through polynomial artificial neural networks and genetic programming. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 3324–3329. Hong Kong (2008)Google Scholar
  7. 7.
    Binner, J., Kendall, G., Chen, S.H. (eds.): Applications of artificial intelligence in finance and economics. Adv. Econom. 19. Elsevier (2004)Google Scholar
  8. 8.
    Burke, E., MacCloumn, B., Meisels, A., Petrovic, S., Qu, R.: A graph-based hyper heuristic for timetabling problems. Eur. J. Oper. Res. 176, 177–192 (2006)CrossRefGoogle Scholar
  9. 9.
    Cao, L., Tay, F.: Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans. Neural Netw. 14, 1506–1518 (2006)CrossRefGoogle Scholar
  10. 10.
    Chen, S.H.: Genetic Algorithms and Genetic Programming in Computational Finance. Springer, New York, LLC (2002)CrossRefGoogle Scholar
  11. 11.
    Cowling, P., Chakhlevitch, K.: Hyperheuristics for Managing a Large Collection of Low Level Heuristics to Schedule Personnel, vol. 2, pp. 1214–1221 (2003). doi:10.1109/CEC.2003.1299807
  12. 12.
    Dempsey, I., O’Neill, M., Brabazon, A.: Live trading with grammatical evolution. In: Proceedings of the Grammatical Evolution Workshop (2004)Google Scholar
  13. 13.
    Edwards, R., Magee, J.: Technical Analysis of Stock Trends. New York Institute of Finance (1992)Google Scholar
  14. 14.
    Gestel, T., Suykens, J., Baestaens, D.E., Lambrechts, A., Lanckriet, G., Vandaele, B., Moor, B., Vandewalle, J.: Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Trans. Neural Netw. 12, 809–821 (2001)CrossRefGoogle Scholar
  15. 15.
    Hart, E., Ross, P., Nelson, J.: Solving a real-world problem using an evolving heuristically driven schedule builder. Evol. Comput. 6(1), 61–80 (1998)CrossRefGoogle Scholar
  16. 16.
    Huang, W., Nakamori, Y., Wang, S.Y.: Forecasting stock market movement direction with support vector machine. Comput. Oper. Res. 32(10), 2513–2522 (2005)CrossRefMATHGoogle Scholar
  17. 17.
    Kablan, A.: Adaptive Neuro Fuzzy Inference Systems for High Frequency Financial Trading and Forecasting, pp. 105–110 (2009). doi:10.1109/ADVCOMP.2009.23
  18. 18.
    Kampouridis, M., Tsang, E.: EDDIE for investment opportunities forecasting: extending the search space of the GP. In: Proceedings of the IEEE Conference on Evolutionary Computation, pp. 2019–2026. Barcelona, Spain (2010)Google Scholar
  19. 19.
    Kampouridis, M., Tsang, E.: Using hyperheuristics under a GP framework for financial forecasting. In: Coello Coello, C.A. (ed.) Proc. Fifth International Conference on Learning and Intelligent Optimization (LION5). Lecture Notes in Computer Science 6683, pp.16–30. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  20. 20.
    Koza, J.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA, MIT Press (1992)MATHGoogle Scholar
  21. 21.
    Larranaga, P., Lozano, J.: Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation. Norwell, MA, Kluwer (2001)Google Scholar
  22. 22.
    Li, J.: FGP: a genetic programming-ased financial forecasting tool. Ph.D. thesis, Department of Computer Science, University of Essex (2001)Google Scholar
  23. 23.
    Martinez-Jaramillo, S.: Artificial financial markets: an agent-based approach to reproduce stylized facts and to study the red queen effect. Ph.D. thesis, CFFEA, University of Essex (2007)Google Scholar
  24. 24.
    Özcan, E., Bilgin, B., Korkmaz, E.E.: A comprehensive analysis of hyper-heuristics. Intelligent Data Analysis 12(1), 3–23 (2008)Google Scholar
  25. 25.
    Poli, R., Langdon, W., McPhee, N.: A field guide to genetic programming. Lulu.com (2008). Accessed 6 March 2012
  26. 26.
    Sapankevych, N., Sankar, R.: Time series prediction using support vector machines: a survey. IEEE Comput. Intell. Mag. 4(2), 24–38 (2009). doi:10.1109/MCI.2009.932254 CrossRefGoogle Scholar
  27. 27.
    Schulenburg, S., Ross, P.: Strength and money: an LCS approach to increasing returns. Lecture Notes in Computer Science, pp. 291–298. Springer Berlin/Heidelberg (2001)Google Scholar
  28. 28.
    Schulenburg, S., Ross, P.: Explorations in LCS models of stock trading. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) 4th International Workshop Advances in Learning Classifier Systems, IWLCS 2001, vol. 2321, pp. 150–179. Springer Berlin/Heidelberg (2002)Google Scholar
  29. 29.
    Shachmurove, Y.: Business applications of emulative neural networks. Int. J. Bus. 10. http://www.craig.csufresno.edu/ijb/Volumes.htm#V10 (2005). Accessed 6 March 2012
  30. 30.
    Sharma, V., Srinivasan, D.: Evolutionary computation and economic time series forecasting. In: Proceedings of the IEEE Conference on Evolutionary Computation, pp. 188–195. Singapore (2007)Google Scholar
  31. 31.
    Tino, P., Nikolaev, N., Yao, X.: Volatility forecasting with sparse Bayesian kernel models. In: Proceedings of the 4th International Conference on Computational Intelligence in Economics and Finance (CIEF’05), pp. 1150–1153. Salt Lake City, Utah, USA (2005)Google Scholar
  32. 32.
    Tsang, E., Li, J., Markose, S., Er, H., Salhi, A., Iori, G.: EDDIE in financial decision making. J. Manag. Econ. 4(4). http://www.econ.uba.ar/servicios/publicaciones/journal4/contents/contents.htm (2000). Accessed 6 March 2012
  33. 33.
    Tsang, E., Markose, S., Er, H.: Chance discovery in stock index option and future arbitrage, World Scientific. New Mathem. Natural Comp. 1(3), 435–447 (2005)CrossRefMATHGoogle Scholar
  34. 34.
    Tsang, E., Martinez-Jaramillo, S.: Computational finance. IEEE Computational Intelligence Society Newsletter, pp. 3–8 (2004)Google Scholar
  35. 35.
    Wagner, N., Michalewicz, Z.: Adaptive and self-adaptive techniques for evolutionary forecasting applications set in dynamic and uncertain environments. Found. Comp. Intellig. 4, 3–21 (2009)Google Scholar
  36. 36.
    Wagner, N., Michalewicz, Z., Kouja, M., McGregor, R.: Time series forecasting for dynamic environments: the dyfor genetic program model. IEEE Trans. Evol. Comput. 11(4), 433–452 (2007)CrossRefGoogle Scholar
  37. 37.
    Wong, B., Selvi, Y.: Neural network applications in finace: a review and analysis of literature (1990–1996). Inf. Manag. 34, 129–139 (1998)CrossRefGoogle Scholar
  38. 38.
    Yuan, X., Zou, Y.: Technology program financial forecast model based on caco-svm. In: Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on, pp. 1–4 (2009). doi:10.1109/IWISA.2009.5073158
  39. 39.
    Zhang, Q., Sun, J., Tsang, E.: Evolutionary algorithm with guided mutation for the maximum clique problem. IEEE Trans. Evol. Comput. 9(2), 192–200 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  • Michael Kampouridis
    • 1
  • Abdullah Alsheddy
    • 2
  • Edward Tsang
    • 3
  1. 1.School of Computer Science and Electronic EngineeringUniversity of EssexEssexUK
  2. 2.College of Computer and Information Sciences (CCIS)Imam Muhammad Bin Saud Islamic UniversityRiyadhKingdom of Saudi Arabia
  3. 3.Centre for Computational Finance and Economic Agents, School of Computer Science and Electronic EngineeringUniversity of EssexEssexUK

Personalised recommendations