Predicting Trading Signals of Stock Market Indices Using Neural Networks

  • Chandima D. Tilakaratne
  • Musa A. Mammadov
  • Sidney A. Morris
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5360)

Abstract

The aim of this paper is to develop new neural network algorithms to predict trading signals: buy, hold and sell, of stock market indices. Most commonly used classification techniques are not suitable to predict trading signals when the distribution of the actual trading signals, among theses three classes, is imbalanced. In this paper, new algorithms were developed based on the structure of feedforward neural networks and a modified Ordinary Least Squares (OLS) error function. An adjustment relating to the contribution from the historical data used for training the networks, and the penalization of incorrectly classified trading signals were accounted for when modifying the OLS function. A global optimization algorithm was employed to train these networks. The algorithms developed in this study were employed to predict the trading signals of day (t+1) of the Australian All Ordinary Index. The algorithms with the modified error functions introduced by this study produced better predictions.

Keywords

Neural networks Classification Stock market predictions Global optimization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Akbani, R., Kwek, S., Japkowwicz, N.: Appying Support Vector Machines to Imbalanced Datasets. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 39–50. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Caldwell, R.B.: Performances Matrics for Neural Network-based Trdaing System Development. NeuroVe$t J. 3, 22–26 (1995)MathSciNetGoogle Scholar
  3. 3.
    Jordanov, I.: Neural Network Training and Stochastic Global Optimization. In: 9th International Conference on Neural Information Processing, vol. 1, pp. 488–492 (2002)Google Scholar
  4. 4.
    Leung, M.T., Daouk, H., Chen, A.S.: Forecasting stock indices: a comparison of classification and level estimation models. In. J. Fore. 16, 173–190 (2000)Google Scholar
  5. 5.
    Mammadov, M.A.: A new global optimization algorithm based on dynamical systems approach. In: Rubinov, A., Sniedovich, M. (eds.) 6th International Conference on Optimization: Techniques and Applications, Ballarat, Australia (2004)Google Scholar
  6. 6.
    Mammadov, M.A., Rubinov, A.M., Yearwood, J.: Dynamical systems described by relational elasticities with applications to global optimization. In: Jeyakumar, V., Rubinov, A. (eds.) Continuous Optimisation: Current Trends and Applications, pp. 365–387. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Minghu, J., Xiaoyan, Z., Baozong, Y., Xiaofang, T., Biqin, L., Qiuqi, R., Mingyan, J.: A fast hybrid algorithm of global optimization for feedforward neural networks. In: 5th International Conference on Signal Processing, Beijing, China (2000)Google Scholar
  8. 8.
    Pan, H., Tilakaratne, C., Yearwood, J.: Predicting the Australian Stock Market Index Using Neural networks Exploiting Dynamical Swings and Intermarket Influences. J. Resear. and Pract. in IT 37, 43–55 (2005)MATHGoogle Scholar
  9. 9.
    Qi, M., Maddala, G.S.: Economic factors and the stock market: A new perspective. J. Fore 18, 151–166 (1999)Google Scholar
  10. 10.
    Refenes, A.N., Bentz, Y., Bunn, D.W., Burgess, A.N., Zapranis, A.D.: Financial Time Series Modelling with Discounted Least Squares Backpropagation. Neurocomp. 14, 123–138 (1995)CrossRefGoogle Scholar
  11. 11.
    Tilakaratne, C.D.: A Study of Intermarket Influence on the Australian All Ordinary Index at Different Time Periods. In: 2nd Australian Business and Behavioural Seiences Association International Conference, Adelaide, Australia (2006)Google Scholar
  12. 12.
    Tilakaratne, C.D., Mammadov, M.A., Hurst, C.P.: Quantification of Intermarket Influence Based on the Global Optimization and Its Application for Stock Market Prediction. In: International Workshop on Integrating AI and Data Mining (AIDM 2006), Hobart, Tasmania, Australia (2006), http://doi.ieeecomputersociety.org/10.1109/AIDM.2006.14
  13. 13.
    Tilakaratne, C.D., Mammadov, M.A., Morris, S.A.: Effectiveness of Using Quantified Intermarket Influence for Predicting Trading signals of Stock Markets. In: 6th Australian Data Mining Conference (AusDM 2007), Gold Coast, Australia (2007), http://crpit.com/confpapers/CRPITV70Tilakaratne.pdf
  14. 14.
    Tilakaratne, C.D., Morris, S.A., Mammadov, M.A., Hurst, C.P.: Predicting Stock Market Index Trading Signals Using Neural Networks. In: 14th Annual Global Finance Conference (GFC 2007), Melbourne, Australia (2007)Google Scholar
  15. 15.
    Tilakaratne, C.D., Morris, S.A., Mammadov, M.A., Hurst, C.P.: Quantification of Intermarket Influence on the Australian All Ordinary Index Based on Optimization Techniques. ANZIAM J. 48, C104–C118 (2007)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Wu, Y., Zhang, H.: Forward Premiums as Unbiased Predictors of Future Currency Depreciation: A Non-parametric Analysis. J. Int. Mon. and Fin. 16, 609–623 (1997)CrossRefGoogle Scholar
  17. 17.
    Yao, J., Tan, C.L., Poh, H.L.: Neural Networks for Technical Analysis: A Study on KLCI. Int. J. Theo. and App. Fin. 2, 221–241 (1999)CrossRefMATHGoogle Scholar
  18. 18.
    Yao, J., Tan, C.L.: Time Dependent Directional Profit Model for Financial Time Series Forecasting. In: IEEE-INNS-ENNS Internationsl Joint Conference on Neural Networks (IJCNN 2000), Como, Italy (2000)Google Scholar
  19. 19.
    Ye, H., Lin, Z.: Global optimization of neural network weights using subenergy tunneling function and ripple search. In: 2003 International Symposium on Circuits and Systems: ISCAS 2003, vol. 5, pp. 725–728 (2003), http://ieeexplore.ieee.org/xpl

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Chandima D. Tilakaratne
    • 1
    • 2
  • Musa A. Mammadov
    • 2
  • Sidney A. Morris
    • 2
  1. 1.Department of StatisticsUniversity of ColomboColombo 3Sri Lanka
  2. 2.Center for Informatics and Applied Optimization School of Information Technology and Mathematical SciencesUniversity of BallaratBallaratAustralia

Personalised recommendations