Accuracy of MLP Based Data Visualization Used in Oil Prices Forecasting Task

  • Aistis Raudys
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)


We investigate accuracy, neural network complexity and sample size problem in multilayer perceptron (MLP) based (neuro-linear) feature extraction. For feature extraction we use weighted sums calculated in hidden units of the MLP based classifier. Extracted features are utilized for data visualisation in 2D and 3D spaces and interactive formation of the pattern classes. We show analytically how complexity of feature extraction algorithm depends on the number of hidden units. Sample size – complexity relations investigated in this paper showed that reliability of the neuro-linear feature extraction could become extremely low if number of new features is too high. Visual interactive inspection of data projection may help an investigator to look differently at the forecasting problem of the financial time series.


Feature extraction Data mapping Sample size Neural network 


  1. 1.
    Fama, E.F.: Efficient capital markets: A review of theory and empirical work. Journal of Finance 25, 383–417 (1970)CrossRefGoogle Scholar
  2. 2.
    Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Acad. Press, NY (1990)zbMATHGoogle Scholar
  3. 3.
    Duda, P.E., Hart, R.O., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, NY (2000)Google Scholar
  4. 4.
    Raudys, S.: Statistical and Neural Classifiers: An integrated approach to design. Springer, NY (2001)zbMATHGoogle Scholar
  5. 5.
    Raudys, A., Long, J.A.: MLP based linear feature extraction for nonlinearly separable data. Pattern Analysis and Applications 4(4), 227–234 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Sammon, J.W.: An optimal discriminant plane. IEEE Trans Computers C-19, 826–829 (1970)Google Scholar
  7. 7.
    Foley, D.H., Sammon, J.W.J.: An optimal set of discriminant vectors. IEEE Trans. on Computers  C-24, 281–289 (1975)zbMATHCrossRefGoogle Scholar
  8. 8.
    Koford, J.S., Groner, G.F.: The use of an adaptive threshold element to design a linear optimal pattern classifier. IEEE Transactions on Information Theory  IT-2, 42–50 (1966)Google Scholar
  9. 9.
    Skurichina, M., Raudys, S., Duin, R.P.W.: K-nearest neighbors directed noise injection in multilayer perceptron training. IEEE Trans. on Neural Networks 11, 504–511 (2000)Google Scholar
  10. 10.
    Adamson, D.M.: Soviet Gas and European-Security. Energy Policy  13 (1), 13–26 (1985)Google Scholar
  11. 11.
    Yousefi, A., Wirjanto, T.S.: The empirical role of the exchange rate on the crude-oil price formation. Energy Economics 26(5), 783–799 (2004)Google Scholar
  12. 12.
    Leduc, S., Sill, K.: A quantitative analysis of oil-price shocks, systematic monetary policy, and economic downturns. J. of Monetary Economics 51(4), 781–808 (2004)Google Scholar
  13. 13.
    Raudys, A., Mockus, J.: Comparison of ARMA and multilayer perceptron based methods for economic time series forecasting. Informatica 10(2), 231–244 (1999)Google Scholar
  14. 14.
    Kittler, J., Roli, F. (eds.): Multiple Classifier Systems. LNCS, vol. 1857, 2096, 2364, 2709, 3077. Springer, NY (2000–2004)Google Scholar
  15. 15.
    Wei, H., Lai, K.K., Nakamori, Y., Wang, S.Y.: Forecasting foreign exchange rates with artificial neural networks: A review. Int. J. on Information Technology and Decision Making 3(1), 145–165 (2004)CrossRefGoogle Scholar
  16. 16.
    Zliobaite, I., Raudys, S.: Prediction of commodity prices in rapidly changing environments. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds.) ICAPR 2005. LNCS, vol. 3686, pp. 154–163. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Aistis Raudys
    • 1
  1. 1.Institute of Mathematics and InformaticsVilniusLithuania

Personalised recommendations