Learning Predictive Models for Financial Time Series by Using Agent Based Simulations

  • Filippo Neri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7190)

Abstract

In this work, we discuss a computational technique to model financial time series combining a learning component with a simulation one. An agent based model of the financial market is used to simulate how the market will evolve in the short term while the learning component based on evolutionary computation is used to optimize the simulation parameters. Our experimentations on the DJIA and SP500 time series show the effectiveness of our learning simulation system in their modeling. Also we test its robustness under several experimental conditions and we compare the predictions made by our system to those obtained by other approaches. Our results show that our system is as good as, if not better than, alternative approaches to modeling financial time series. Moreover we show that our approach requires a simple input, the time series for which a model has to be learned, versus the complex and feature rich input to be given to other systems thanks to the ability of our system to adjust its parameters by learning.

Keywords

Agent based modeling Simulated annealing Differential evolution Financial time series Prediction of the SP500 and DJIA time series 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bonabeau, E.: Agent-based modeling: Methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences 99, 7280–7287 (2002)CrossRefGoogle Scholar
  2. 2.
    Epstein, J.M., Axtell, R.: Growing artificial societies: social science from the bottom up. The Brookings Institution, Washington, DC, USA (1996)Google Scholar
  3. 3.
    Neri, F.: Software agents as a simulation tool to study aggregate consumers’ behavior in market places. IASR Journal of Advanced Research in Computer Science 1, 32–43 (2009)Google Scholar
  4. 4.
    Neri, F.: PIRR: a methodology for distributed network management in mobile networks. WSEAS Transaction on Information Science and Applications 5, 306–311 (2008)Google Scholar
  5. 5.
    Lebaron, B.: Agent based computational finance: Suggested readings and early research. Journal of Economic Dynamics and Control 24, 679–702 (1998)CrossRefGoogle Scholar
  6. 6.
    Tesfatsion, L.: Agent-based computational economics: Growing economies from the bottom up. Artif. Life 8, 55–82 (2002)CrossRefGoogle Scholar
  7. 7.
    Hoffmann, A.O.I., Delre, S.A., von Eije, J.H., Jager, W.: Artificial multi-agent stock markets: Simple strategies, complex outcomes. In: Advances in Artificial Economics. Lecture Notes in Economics and Mathematical Systems, vol. 584, pp. 167–176. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  8. 8.
    Kendall, G., Su, Y.: A multi-agent based simulated stock market - testing on different types of stocks. In: Congress on Evolutionary Computation CEC 2003, pp. 2298–2305 (2003)Google Scholar
  9. 9.
    Kirkpatrick, C., Dahlquist, J.: Technical Analysis: The Complete Resource for Financial Market Technicians. FT Press (2006)Google Scholar
  10. 10.
    Schulenburg, S., Ross, P.: An Adaptive Agent Based Economic Model. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 1999. LNCS (LNAI), vol. 1813, pp. 263–284. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  11. 11.
    Dempster, M.A.H., Payne, T.W., Romahi, Y., Thompson, G.W.P.: Computational learning techniques for intraday fx trading using popular technical indicators. IEEE Transactions on Neural Networks 12, 744–754 (2001)CrossRefGoogle Scholar
  12. 12.
    Takahashi, H., Terano, T.: Analyzing the Influence of Overconfident Investors on Financial Markets through Agent-based Model. In: Yin, H., Tino, P., Corchado, E., Byrne, W., Yao, X. (eds.) IDEAL 2007. LNCS, vol. 4881, pp. 1042–1052. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Arthur, W.B., Holland, J.H., LeBaron, B., Palmer, R., Taylorm, P.: Asset pricing under endogenous expectation in an artificial stock market. In: The Economy as an Evolving Complex System II. Santa Fe Institute Studies in the Sciences of Complexity Lecture Notes, pp. 15–44 (1997)Google Scholar
  14. 14.
    Neri, F.: Using software agents to simulate how investors’ greed and fear emotions explain the behavior of a financial market. In: WSEAS Conference ICOSSE 2009, Genoa, Italy, pp. 241–245 (2009)Google Scholar
  15. 15.
    Majhi, R., Sahoo, G., Panda, A., Choubey, A.: Prediction of sp500 and djia stock indices using particle swarm optimization techniques. In: Congress on Evolutionary Computation 2008, pp. 1276–1282. IEEE Press (2008)Google Scholar
  16. 16.
    Kitov, I.: Predicting conocophillips and exxon mobil stock price. Journal of Applied Research in Finance 2, 129–134 (2009)Google Scholar
  17. 17.
    Cesa, A.: Discussion about how financial markets work: an investment manager perspective. Personal correspondance with the author (2009)Google Scholar
  18. 18.
    Goldberg, D.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  19. 19.
    Neri, F.: Traffic packet based intrusion detection: decision trees and generic based learning evaluation. WSEAS Transaction on Computers 4, 1017–1024 (2005)Google Scholar
  20. 20.
    Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, California (1993)Google Scholar
  21. 21.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Foundations, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)Google Scholar
  22. 22.
    Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220, 671–680 (1983)MATHCrossRefMathSciNetGoogle Scholar
  23. 23.
    Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization 11, 341–359 (1997)MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Neri, F., Saitta, L.: Exploring the power of genetic search in learning symbolic classifiers. IEEE Trans. on Pattern Analysis and Machine Intelligence PAMI-18, 1135–1142 (1996)Google Scholar
  25. 25.
    Kennedy, J., Eberhard, R.: Particle swarm optimization. In: Int. Conf. on Neural Networks, pp. 1942–1948. IEEE Press (1995)Google Scholar
  26. 26.
    Zirilli, J.: Financial prediction using Neural Networks. International Thompson Computer Press (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Filippo Neri
    • 1
  1. 1.Dept. of Computer ScienceUniversity of NaplesNaplesItaly

Personalised recommendations