Advertisement

A New Computational Method of Input Selection for Stock Market Forecasting with Neural Networks

  • Wei Huang
  • Shouyang Wang
  • Lean Yu
  • Yukun Bao
  • Lin Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3994)

Abstract

We propose a new computational method of input selection for stock market forecasting with neural networks. The method results from synthetically considering the special feature of input variables of neural networks and the special feature of stock market time series. We conduct the experiments to compare the prediction performance of the neural networks based on the different input variables by using the different input selection methods for forecasting S&P 500 and NIKKEI 225. The experiment results show that our method performs best in selecting the appropriate input variables of neural networks.

Keywords

Neural Network Bayesian Information Criterion Prediction Performance Radial Basis Function Network Stock Index 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Hall, J.W.: Adaptive selection of US stocks with neural nets. In: Deboeck, G.J. (ed.) Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets, pp. 45–65. Wiley, New York (1994)Google Scholar
  2. 2.
    Huang, W., Lai, K.K., Nakamori, Y., Wang, S.Y.: Forecasting foreign exchange rates with artificial neural networks: a review. International Journal of Information Technology & Decision Making 3, 145–165 (2004)CrossRefGoogle Scholar
  3. 3.
    Huang, W., Nakamori, Y., Wang, S.Y.: Forecasting Stock Market Movement Direction with Support Vector Machine. Computers & Operations Research 32, 2513–2522 (2005)MATHCrossRefGoogle Scholar
  4. 4.
    Neeraj, M., Pankaj, J., Kumar, L.A., Goutam, D.: Artificial neural network models for forecasting stock price index in Bombay Stock Exchange. Working Papers with number 2005-10-01 in Indian Institute of Management Ahmedabad, Research and Publication Department (2005)Google Scholar
  5. 5.
    Yim, J.: A comparison of neural networks with time series models for forecasting returns on a stock market index. In: Hendtlass, T., Ali, M. (eds.) IEA/AIE 2002. LNCS (LNAI), vol. 2358, p. 25. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  6. 6.
    Yu, S.W.: Forecasting and arbitrage of the Nikkei stock index futures: an application of backpropagation networks. Asia-Pacific Financial Markets 6, 341–354 (1999)MATHCrossRefGoogle Scholar
  7. 7.
    Qi, M., Zhang, G.P.: An investigation of model selection criteria for neural network time series forecasting. European Journal of Operational Research 132, 666–680 (2001)MATHCrossRefGoogle Scholar
  8. 8.
    Embrechts, M., Cader, M., Deboeck, G.J.: Nolinear dimensions of foreign exchange, stock and bond markets. In: Deboeck, G.J. (ed.) Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets, pp. 297–313. Wiley, New York (1994)Google Scholar
  9. 9.
    Oh, K.J., Kim, K.: Analyzing stock market tick data using piecewise nonlinear model. Expert Systems with Applications 22, 249–255 (2002)CrossRefGoogle Scholar
  10. 10.
    Zhang, G.P.: Neural Networks in Business Forecasting. Idea Group Inc., USA (2003)Google Scholar
  11. 11.
    Huang, W., Nakamori, Y., Wang, S.Y., Zhang, H.: Select the size of training set for financial forecasting with neural networks. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3497, pp. 879–884. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wei Huang
    • 1
    • 2
  • Shouyang Wang
    • 2
  • Lean Yu
    • 2
  • Yukun Bao
    • 1
  • Lin Wang
    • 1
  1. 1.School of ManagementHuazhong University of Science and TechnologyWuHanChina
  2. 2.Institute of Systems ScienceAcademy of Mathematics and Systems Sciences, Chinese Academy of SciencesBeijingChina

Personalised recommendations