Annals of Operations Research

, Volume 75, Issue 0, pp 335–353 | Cite as

A stock selection DSS combining AI and technical analysis

  • Seng-cho T. Chou
  • Hsien-jung Hsu
  • Chau-chen Yang
  • Feipei Lai
Article

Abstract

Both technical analysis and artificial intelligence are popular and promising approaches for the construction of intelligent financial application systems, but any particular method alone might not be sufficient. Instead of pursuing the construction of a perfect system using any one particular technique, this paper focuses on the study of the Intelligent Stock Selection Decision Support System (ISSDSS) that adopts both traditional technical analysis and artificial intelligence in dealing with the stock selection problem. ISSDSS analyzes the Taiwan stock market using various technical analysis techniques including technical indicators, charts analysis, Japanese candlesticks philosophy, and Dow theory, giving the basis for the evaluation of the price and trend of stocks, trading signals, and trading prices. AI techniques built upon fuzzy decision rules are employed to double-check the results from technical analysis. The performance of ISSDSS was evaluated by simulating the stock selection in the Taiwan stock market from January 1990 to April 1995. The result confirms that the synergy of technical analysis and artificial intelligence outperforms systems using any one particular technique alone.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    E. Cox, A model-free trainable fuzzy system for the analysis of financial time-series data, 2nd International Conference on Artificial Intelligence Applications on Wall Street, 1993, pp. 280–285.Google Scholar
  2. [2]
    G.J. Deboeck, Trading On The Edge, Wiley, 1994.Google Scholar
  3. [3]
    G. Du, Apply Technical Indices to Taiwan Stock Market, Fei-Fan Inc., Taiwan, 1992.Google Scholar
  4. [4]
    R.D. Edwards and J. Magee, Technical Analysis of Stock Trends, John Magee, Inc., 1974.Google Scholar
  5. [5]
    M.L. Gargano, P. Chamoun and D.L. Von Kleeck, Using genetic algorithms to solve financial portfolio problems related to optimal allocation, portfolio insurance, and performance, 2nd International Conference on Artificial Intelligence Applications on Wall Street, 1993, pp. 137–143.Google Scholar
  6. [6]
    D.E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.Google Scholar
  7. [7]
    Y. Hiemstra, A stock market forecasting support system based on fuzzy logic, Proceedings of the 27th Annual Hawaii International Conference on System Sciences, 1994, pp. 281–287.Google Scholar
  8. [8]
    G.S. Jang, F. Lai, B.W. Jiang, C.C. Pan and L.H. Chien, An intelligent stock portfolio management system based on short-term trend prediction using dual-module neural networks, Proceedings of the International Conference on Artificial Neural Networks, Finland, 1991, pp. 447–452.Google Scholar
  9. [9]
    P.J. Kaufman, The New Commodity Trading Systems and Methods, Wiley, New York, 1987.Google Scholar
  10. [10]
    C.C. Klimasauskas, Hybrid fuzzy encodings for improved backpropagation performance, Advanced Technology for Developers (September 1992).Google Scholar
  11. [11]
    G.J. Klir and T.A. Folger, Fuzzy Sets, Uncertainty, and Information, Prentice-Hall, 1992.Google Scholar
  12. [12]
    B. Kosko, Neural Networks and Fuzzy Systems, A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall, 1992.Google Scholar
  13. [13]
    H. Markowitz, Portfolio selection, Journal of Finance, (March 1952).Google Scholar
  14. [14]
    G.L. Morris, Candle Power, International Publishing Company, Taiwan, 1994.Google Scholar
  15. [15]
    J.R. Quinlan, Induction of decision trees, Machine Learning 1(1986)81–106.Google Scholar
  16. [16]
    E. Rich and K. Knight, Artificial Intelligence, McGraw-Hill, 1993.Google Scholar
  17. [17]
    R.J. Bauer, Jr., Genetic Algorithms and Investment Strategies, Wiley, 1994.Google Scholar
  18. [18]
    F. Wong, Hybrid neural network for stock selection, 2nd International Conference on Artificial Intelligence Applications on Wall Street, 1993, pp. 294–301.Google Scholar
  19. [19]
    T. Yamaguchi and Y. Tachibana, A framework for rule base refinement in a stock market technical analysis — towards discovering anomaly from Granville's Law, 2nd International Conference on Artificial Intelligence Applications on Wall Street, 1993, pp. 259–268.Google Scholar

Copyright information

© Kluwer Academic Publishers 1997

Authors and Affiliations

  • Seng-cho T. Chou
  • Hsien-jung Hsu
  • Chau-chen Yang
  • Feipei Lai

There are no affiliations available

Personalised recommendations