One Day Prediction of NIKKEI Index Considering Information from Other Stock Markets

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3070)


A task of a stock index prediction is presented in this paper. Several issues are considered. The data is gathered at the concerned stock market (NIKKEI) and two other markets (NASDAQ and DAX). The data contains not only original numerical values from the markets but also indicators pre-processed in terms of technical analysis, i.e. the oscillators are calculated and the structures of a value chart are extracted. Selected data is input to a neural network that is functionally divided into separate modules. The prediction goal was next day opening value of Japanese stock market index NIKKEI with consideration of German and USA stock markets’ indexes. The average prediction error on the test set equals 43 points and the average percentage prediction error is equal to 0.27% while the average index volatility equals 0.96%.


Stock Market Independent Component Analysis Technical Analysis Data Stock Market Index Average Percentage Error 
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.
    Mantegna, R., Stanley, E.: An introduction to econophysics. In: Correlations and complexity in finance, Cambridge University Press, Cambridge (2000)Google Scholar
  2. 2.
    Dempster, T.P., et al.: Computational learning techniques for intraday fx trading using popular technical indicators. IEEE Transactions on Neural Networks 12, 744–754 (2001)CrossRefGoogle Scholar
  3. 3.
    Podding, T., Rehkegler, H.: A “world” model of integrated financial markets using artificial neural networks. Neurocomputing 10, 251–273 (1996)CrossRefGoogle Scholar
  4. 4.
    Chenoweth, T., Obradović, Z.: A multi-component nonlinear prediction system for the s&p 500 index. Neurocomputing 10, 275–290 (1996)CrossRefGoogle Scholar
  5. 5.
    Fu, H.C., Lee, Y.P., et al.: Divide-and-conquer learning and modular perceptron networks. IEEE Transactions on Neural Networks 12, 250–263 (2001)CrossRefGoogle Scholar
  6. 6.
    Khotanzad, A., Elragal, H., et al.: Combination of artificial neural-network forecasters for prediction of natural gas consumption. IEEE Transactions on Neural Networks 11, 464–473 (2000)CrossRefGoogle Scholar
  7. 7.
    Murphy, J.: Technical analysis of the financial markets. New York Institiute of Finance (1999)Google Scholar
  8. 8.
    Tony Gestel, J.S., et al.: Financial time series prediction using least squares support vector machnies within the evidence framework. IEEE Transactions on Neural Networks 12, 809–820 (2001)CrossRefGoogle Scholar
  9. 9.
    Peter Tino, C.S., et al.: Financial volatility trading using recurent neural networks. IEEE Transactions on Neural Networks 12, 865–874 (2001)CrossRefGoogle Scholar
  10. 10.
    Back, A., Trappenberg, T.: Selecting inputs for modeling using normalized higher order statistics and independent component analysis. IEEE Transactions on Neural Networks 12, 612–617 (2001)CrossRefGoogle Scholar
  11. 11.
    Refenes, A., Holt, W.: Forecasting volatility with neural regression: A contribution to model adequacy. IEEE Transactions on Neural Networks 12, 850–864 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  1. 1.Faculty of Mathematics and Information ScienceWarsaw University of TechnologyWarsawPoland

Personalised recommendations