Advertisement

Designing Loss-Aware Fitness Function for GA-Based Algorithmic Trading

  • Yuya AraiEmail author
  • Ryohei Orihara
  • Hiroyuki Nakagawa
  • Yasuyuki Tahara
  • Akihiko Ohsuga
Part of the Studies in Computational Intelligence book series (SCI, volume 489)

Abstract

In these days, an algorithmic trading in stock or foreign exchange (henceforth forex) market is in fashion, and needs for automatically performing stable asset management are growing. Machine learning techniques are increasingly used to construct trading rules of the algorithmic trading, as researches on the algorithmic trading advance. Our study aims to build an automatic trading agent, and in this paper, we concentrate in designing a module which determines trading rules by machine learning. We use Genetic Algorithm (henceforth GA), and we build trading rules by learning parameters of technical indices. Our contribution in this paper is that we propose new fitness functions in GA, in order to make them robuster to change of market trends. Although profits were used as a fitness function in the previous study, we propose the fitness functions which pay more attention to not making a loss than to gaining profits. As a result of our experiment using real TSE(Tokyo Stock Exchange) data for eight years, the proposed method has outperformed the previous method in terms of gained profits.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lu, C.-J., Chiu, C.-C., Yang, J.-L.: Integrating nonlinear independent component analysis and neural network in stock price prediction. In: Chien, B.-C., Hong, T.-P., Chen, S.-M., Ali, M. (eds.) IEA/AIE 2009. LNCS, vol. 5579, pp. 614–623. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Neto, M.C.A., Calvalcanti, G.D.C., Ren, T.I.: Financial time series prediction using exogenous series and combined neural networks. In: IJCNN 2009, pp. 2578–2585 (2009)Google Scholar
  3. 3.
    Yu, T.H.K., Huarng, K.H.: A Bivariate Fuzzy Time Series Model to Forecast the TAIEX. Expert Systems with Applications 34, 2945–2952 (2008)CrossRefGoogle Scholar
  4. 4.
    Chen, C.D., Chen, S.M.: A New Method to Forecast the TAIEX Based on Fuzzy Time Series. In: Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics, San Antonio, Texas, pp. 3550–3555 (2009)Google Scholar
  5. 5.
    Chen, S.-M., Chu, H.-P.: TAIEX forecasting based on fuzzy time series and the automatically generated weights of defuzzified forecasted fuzzy variations of multiple-factors. In: Pan, J.-S., Chen, S.-M., Nguyen, N.T. (eds.) ICCCI 2010, Part II. LNCS, vol. 6422, pp. 441–450. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Chen, Y., et al.: A portfolio optimization model using Genetic Network Programming with control nodes. Expert Syst., 10735–10745 (2009)Google Scholar
  7. 7.
    Matsui, K., Sato, H.: A comparison of genotype representations to acquire stock trading strategy using genetic algorithms. In: ICAIS 2009, pp. 129–134 (2009)Google Scholar
  8. 8.
    Matsui, K., Sato, H.: Neighborhood evaluation in acquiring stock trading strategy using genetic algorithms. In: SoCPaR 2010, pp. 369–372 (2010)Google Scholar
  9. 9.
  10. 10.
    Sato, H., et al.: A New Generation Alternation Model of Genetic Algorithms and Its Assessment. J. of Japanese Society for Artificial Intelligence 12(5), 734–744 (1997)Google Scholar
  11. 11.
    Syswerda, G.: Uniform Crossover in Genetic Algorithms. In: Proceedings of the Third International Conference on Genetic Algorithms, pp. 2–9 (1989)Google Scholar
  12. 12.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading (1989)zbMATHGoogle Scholar
  13. 13.

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Yuya Arai
    • 1
    Email author
  • Ryohei Orihara
    • 1
  • Hiroyuki Nakagawa
    • 1
  • Yasuyuki Tahara
    • 1
  • Akihiko Ohsuga
    • 1
  1. 1.Graduate School of Information SystemsThe University of Electro-CommunicationsTokyoJapan

Personalised recommendations