Applied Intelligence

, Volume 3, Issue 3, pp 225–248 | Cite as

Intelligent stock trading system with price trend prediction and reversal recognition using dual-module neural networks

  • Gia-Shuh Jang
  • Feipei Lai
  • Bor-Wei Jiang
  • Tai-Ming Parng
  • Li-Hua Chien


This article presents an intelligent stock trading system that can generate timely stock trading suggestions according to the prediction of short-term trends of price movement using dual-module neural networks(dual net). Retrospective technical indicators extracted from raw price and volume time series data gathered from the market are used as independent variables for neural modeling. Both neural network modules of thedual net learn the correlation between the trends of price movement and the retrospective technical indicators by use of a modified back-propagation learning algorithm. Reinforcing the temporary correlation between the neural weights and the training patterns, dual modules of neural networks are respectively trained on a short-term and a long-term moving-window of training patterns. An adaptive reversal recognition mechanism that can self-tune thresholds for identification of the timing for buying or selling stocks has also been developed in our system. It is shown that the proposeddual net architecture generalizes better than one single-module neural network. According to the features of acceptable rate of returns and consistent quality of trading suggestions shown in the performance evaluation, an intelligent stock trading system with price trend prediction and reversal recognition can be realized using the proposed dual-module neural networks.

Key words

Neural networks prediction stock trading 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. Felsen, “Learning pattern recognition techniques applied to stock market forecasting,”IEEE Trans. Systems Man Cybernet., vol. SMC-5, no. 6, pp. 583–594, 1975.Google Scholar
  2. 2.
    J.F. Elder, IV, and M.T. Finn, “Creating ‘optimally complex’ models for forecasting,”Financial Analysts J., pp. 73–79, January–February 1991.Google Scholar
  3. 3.
    D.D. Hawley, J.D. Johnson, and D. Raina, “Artificial neural systems: A new tool for financial decision-making,”Financial Analysts J., pp. 63–72. November–December 1990.Google Scholar
  4. 4.
    E. Schoneburg, “Stock price prediction using neural networks: A project report,”Neurocomputing, vol. 2, pp. 17–27, 1990.Google Scholar
  5. 5.
    T. Kimoto, K. Asakawa, M. Yoda, and M. Takeoka, “Stock market prediction system with modular neural networks,”Proc. IEEE Int. Joint Conf. Neural Networks, 1990, pp. 1–6.Google Scholar
  6. 6.
    F.S. Wong, “Time series forecasting using back-propagation neural networks,”Neurocomputing, vol. 2, pp. 147–159, 1991.Google Scholar
  7. 7.
    G.S. Jang, F. Lai, B.W. Jiang, and L.H. Chien, “An intelligent trend prediction and reversal recognition system using dual-module neural networks,”Proc. First Int. Conf. Artif. Intell. Appl. on Wall Street, New York, 1991, pp. 42–51.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,”Proc. Int. Conf. Artif. Neural Networks, Finland, 1991, pp. 447–452.Google Scholar
  9. 9.
    J. Utans and J. Moody, “Selecting neural network architecture via the prediction risk: Application to corporate bond rating prediction,”Proc. First Int. Conf. Artif. Intell. Appl. on Wall Street, New York, 1991, pp. 35–41.Google Scholar
  10. 10.
    A. Guez, J.L. Eilbert, and M. Kam, “Neural network architecture for control,”IEEE Control Syst. Mag. vol. 8, no. 2, pp. 22–25, April 1988.Google Scholar
  11. 11.
    R.P. Gorman and T.J. Sejnowski, “Analysis of hidden units in a layered network trained to classify sonar targets,”Neural Networks, vol. 1, no. 1, pp. 75–90, 1988.Google Scholar
  12. 12.
    T.J. Sejnowski and C.R. Rosenberg, “Parallel networks that learn to pronounce English text,”Complex Syst., vol. 1, 1987, pp. 145–168.Google Scholar
  13. 13.
    J.J. Murphy,Technical Analysis of the Futures Markets, A Comprehensive Guide to Trading Methods and Applications, New York Institute of Finance: New York, 1986.Google Scholar
  14. 14.
    G.C. Lane,Trading Strategies, Future Symposium International: Tucson, AZ, 1984.Google Scholar
  15. 15.
    K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,”Neural Networks, vol. 2, pp. 359–366, 1989.CrossRefGoogle Scholar
  16. 16.
    D.E. Rumelhart, J.L. McClelland, and the PDP Research Group,Parallel Distributed Processing Explorations in the Microstructure of Cognition. Volume I: Foundations, MIT Press: Cambridge, MA, 1986.Google Scholar
  17. 17.
    S.C. Huang and Y.F. Huang, “Learning algorithms for perceptrons using back-propagation with selective updates,”IEEE Control Syst. Mag. vol. 10, no. 3, pp. 56–61, April 1990.Google Scholar
  18. 18.
    G. Mani, “Lowering variance of decisions by using artificial neural network portfolios,”Neural Computation, vol. 3, pp. 484–486, 1991.Google Scholar
  19. 19.
    T.C. Lee,Structure Level Adaptation for Artificial Neural Networks, Kluwer Academic: Boston, 1991.Google Scholar
  20. 20.
    D.E. Goldberg,Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley: Reading, MA, 1989.Google Scholar
  21. 21.
    J.W. Wilder, Jr.,New Concepts in Technical Trading Systems, Trend Research: Greensboro, NC, 1978.Google Scholar

Copyright information

© Kluwer Academic Publishers 1993

Authors and Affiliations

  • Gia-Shuh Jang
    • 1
  • Feipei Lai
    • 1
  • Bor-Wei Jiang
    • 1
  • Tai-Ming Parng
    • 1
  • Li-Hua Chien
    • 2
  1. 1.Department of Electrical Engineering and Department of Computer Science and Information EngineeringNational Taiwan UniversityTaipeiTaiwan, ROC
  2. 2.Capital Market GroupChina Development CorporationChina

Personalised recommendations