Forecasting stock price is one of the fascinating issues of stock market research. Accurately forecasting stock price, which forms the basis for the decision making of financial investment, is probably the biggest challenge for capital investment industry, which leads it a widely researched area. Time series forecasting and neural network are once commonly used for prediction on stock price. This paper deals with the application of a novel neural network technique, support vector machines (SVMs) regression, in forecasting stock price. The objective of this paper is to examine the feasibility of SVMs regression in forecasting stock price. A data set from shanghai stock market in China is used for the experiment to test the validity of SVMs regression. The experiment shows SVMs regression a valuable method in forecasting the stock price.


Stock price forecasts SVMs regression Machine learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bessler, D.A., Brandt, J.A.: Forecasting livestock prices with individual and composite methods. Applied Economics 13, 513–522 (1981)CrossRefGoogle Scholar
  2. 2.
    Harris, K.S., Leuthold, R.M.: A comparison of alternative forecasting techniques for live stock prices: A case study. North Central J. Agricultural Economics 7, 40–50 (1985)CrossRefGoogle Scholar
  3. 3.
    Dorfman, J.H., Mcintosh, C.S.: Results of a price forecasting competition. American J. Agricultural Economics 72, 804–808 (1990)CrossRefGoogle Scholar
  4. 4.
    Blank, S.C.: Chaos in future markets? A nonlinear dynamic analysis. J. Futures Markets 11, 711–728 (1991)CrossRefGoogle Scholar
  5. 5.
    Chavas, J., Holt, M.T.: Market instability and nonlinear dynamics. American J. Agricultural Economics 75, 113–120 (1993)CrossRefGoogle Scholar
  6. 6.
    Hall, J.W.: Adaptive selection of U.S. stocks with neural nets. In: Deboeck, G.J. (ed.) Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets, Wiley, New York (1994)Google Scholar
  7. 7.
    Yaser, S.A.M., Atiya, A.F.: Introduction to financial forecasting. Applied Intelligence 6, 205–213 (1996)CrossRefGoogle Scholar
  8. 8.
    Grudnitski, G., Osburn, L.: Forecasting S&P and gold futures prices: an application of neural networks. The Journal of Futures Markets 13(6), 631–643 (1993)CrossRefGoogle Scholar
  9. 9.
    Kim, S., Chun, S.: Graded forecasting using an array of bipolar predictions: application of probabilistic neural networks to a stock market index. International Journal of Forecasting 14(3), 323–337 (1998)CrossRefGoogle Scholar
  10. 10.
    Saad, E., Prokhorov, D., Wunsch, D.: Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE Transactions on Neural Networks 9(6), 1456–1470 (1998)CrossRefGoogle Scholar
  11. 11.
    Cheng, W., Wanger, L., Lin, C.: Forecasting the 30-year US treasury bond witha system of neural networks. Journal of Computational Intelligence in Finance 4, 10–16 (1996)Google Scholar
  12. 12.
    Sharda, R., Patil, R.B.: A connectionist approach to time series prediction: an empirical test. In: Trippi, R.R., Turban, E. (eds.) Neural Networks in Finance and Investing, pp. 451–464. Probus Publishing Co., Chicago (1994)Google Scholar
  13. 13.
    Haykin, S.: Neural networks: a comprehensive foundation. Prentice Hall, Englewood CliKs (1999)zbMATHGoogle Scholar
  14. 14.
    Zhang, G.Q., Michael, Y.H.: Neural network forecasting of the British Pound=US Dollar exchange rate. Omega 26(4), 495–506 (1998)CrossRefGoogle Scholar
  15. 15.
    Kaastra, I., Milton, S.B.: Forecasting futures trading volume using neural networks. The Journal of Futures Markets 15(8), 853–970 (1995)CrossRefGoogle Scholar
  16. 16.
    Vapnik, V.N.: The nature of statistical learning theory. Springer, New York (1995)zbMATHGoogle Scholar
  17. 17.
    Schmidt, M.: Identifying speaker with support vector networks. In: Interface 1996 Proceedings, Sydney (1996)Google Scholar
  18. 18.
    Muller, K.R., Smola, A., Scholkopf, B.: Prediction time series with support vector machines. In: Proceedings of International Conference on Artificial Neural Networks, Lausanne, Switzerland, p. 999 (1997)Google Scholar
  19. 19.
    Vapnik, V.N., Golowich, S.E., Smola, A.J.: Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems 9, 281–287 (1996)Google Scholar
  20. 20.
    Thomason, M.: The practitioner methods and tool. Journal of Computational Intelligence in Finance 7(3), 36–45 (1999)Google Scholar
  21. 21.
    Keerthi, S.S., Lin, C.-.J.: Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Computation 15(7), 1667–1689Google Scholar
  22. 22.
    Lin, H.-T., Lin, C.-J.: A study on sigmoid kernels for SVM and the training of non- PSD kernels by SMO-type methods. Technical report, Department of Computer Science and Information Engineering, National Taiwan University, Available at

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yukun Bao
    • 1
  • Yansheng Lu
    • 2
  • Jinlong Zhang
    • 1
  1. 1.Department of Management Scince & information System, School of ManagementHuazhong University of Science and TechnologyWuhanChina
  2. 2.College of Computer ScienceHuazhong University of Science and TechnologyWuhanChina

Personalised recommendations