Combination of Linear and General Regression Neural Network for Robust Short Term Financial Prediction

  • Tony Jan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2690)


In business applications, robust short term prediction is important for survival. Artificial neural network (ANN) have shown excellent potential however it needs better extrapolation capacity in order to provide reliable short term prediction. In this paper, a combination of linear regression model in parallel with general regression neural network is introduced for short term financial prediction. The experiment shows that the proposed model achieves comparable prediction performance to other conventional prediction models.


Mean Square Error Radial Basis Function Prediction Performance Linear Regression Model Probabilistic Neural Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wilson, C.L.: Self-organising neural networks for trading common stocks. In: Proc. IEEE World Congr. Neural Networks, Orlando, FL, pp. 3657–3661 (1994)Google Scholar
  2. 2.
    Konstenius, J.: Mirrored Markets. In: Proc. IEEE World Congress on Neural Network, Orlando, Florida, pp. 3671–3675 (1994)Google Scholar
  3. 3.
    Lowe, D.: Novel exploitation of neural network methods in financial markets. In: Proc. IEEE World Congr. Neural Networks, Orlando, FL, pp. 3623–3627 (1994)Google Scholar
  4. 4.
    Specht, D.F.: Probabilistic Neural Networks. Int. Neural Network Soc., Neural Networks 3, 109–118 (1990)CrossRefGoogle Scholar
  5. 5.
    Moody, J., Darken, C.: Fast learning in networks of locally tuned processing units. Neural Comput. 1(2), 281–294 (1989)CrossRefGoogle Scholar
  6. 6.
    Moody, J., Darken, C.: Learning localized receptive fields. In: Touretzky, Hinton, Sejnowski (eds.) Proc. 1988 Connectionist Models Summer Sch., pp. 133–143. Morgan-Kaufmann, San Francisco (1988)Google Scholar
  7. 7.
    Powell, M.J.D.: Radial basis functions for multivariate interpolation: A review, Tech. Rept. DAMPT 1985/NA 12 Dept. Appl. Math. Theoretical Phys. Cambridge, MA (November 1974)Google Scholar
  8. 8.
    Broomhead, D.S., Lowe, D.: Radial basis functions, multi-variable functional interpolation and adaptive networks. Royal Signals Radar Est. Memo. 4248, March 28 (1988)Google Scholar
  9. 9.
    Albus, J.S.: A new approach to manipulator control: The cerebellar model articulation controller (CMAC). J. Dyn. Syst. Meas. Contr, 220–227 (September 1975)Google Scholar
  10. 10.
    Nadaraya, E.A.: On estimating regression. Theory Probab. Appl. 9, 141–142 (1964)CrossRefGoogle Scholar
  11. 11.
    Hayes, M.H.: Statistical Digital Signal Processing and Modeling. John Wiley & Sons, Inc. Chichester (1996)Google Scholar
  12. 12.
    Krusienski, D.J., Jenkins, K.: Comparative analysis of neural network filters and adaptive Volterra filters. In: Proceedings of the 44th IEEE 2001 Midwest Symposium, 1st edn., vol. 1, pp. 49–52 (2001)Google Scholar
  13. 13.
    Haykin, S.: em Neural Networks: comprehensive foundations. Prentice Hall, Upper Saddle River (1996)Google Scholar
  14. 14.
    Jan, T., Zaknich, A.: Adjustable model from linear to nonlinear regression. In: Proceedings of IEEE Conference on International Joint Conference on Neural Networks, Washington DC, USA, July 10th-16th, p. 635 (1999)Google Scholar
  15. 15.
    Huang, X., Ma, X., Li, X., Fu, Y., Lu, J.: Study on recognition of speech based on HMM/MLP hybrid network. In: Signal Processing Proceedings, 2000, WCCC-ICSP 2000, 2nd edn. 5th International Conference, vol. 2, pp. 718–721 (2000)Google Scholar
  16. 16.
    Miller, W.T., Glantz, F.H., Kraft, L.G.: CMAC: An association neural network alternative to backpropagation. In: Proc. IEEE, vol. 78, pp. 1561–1567 (Oct. 1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Tony Jan
    • 1
  1. 1.Department of Computer SystemsUniversity of Technology, SydneyBroadwayAustralia

Personalised recommendations