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

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.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  E. Fama.  EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[3]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[4]  Sarunas Raudys,et al.  Prediction of Commodity Prices in Rapidly Changing Environments , 2005, ICAPR.

[5]  Kin Keung Lai,et al.  Forecasting Foreign Exchange Rates With Artificial Neural Networks: A Review , 2004, Int. J. Inf. Technol. Decis. Mak..

[6]  David M. Adamson.  Soviet gas and European security , 1985 .

[7]  Aistis Raudys,et al.  MLP Based Linear Fea ure Ex rac ion for Nonlinearly Separable Data , 2001, Pattern Analysis & Applications.

[8]  Maneesha Singh,et al.  Pattern Recognition and Data Mining, Third International Conference on Advances in Pattern Recognition, ICAPR 2005, Bath, UK, August 22-25, 2005, Proceedings, Part I , 2005, International Conference on Advances in Pattern Recognition.

[9]  John W. Sammon,et al.  An Optimal Set of Discriminant Vectors , 1975, IEEE Transactions on Computers.

[10]  Tony S. Wirjanto,et al.  The empirical role of the exchange rate on the crude-oil price formation , 2004 .

[11]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[12]  John W. Sammon,et al.  An Optimal Discriminant Plane , 1970, IEEE Transactions on Computers.

[13]  J. S. Koford,et al.  The use of an adaptive threshold element to design a linear optimal pattern classifier , 1966, IEEE Trans. Inf. Theory.

[14]  Josef Kittler,et al.  Multiple Classifier Systems , 2004, Lecture Notes in Computer Science.

[15]  Aistis Raudys,et al.  Comparison of ARMA and Multilayer Perceptron Based Methods for Economic Time Series Forecasting , 1999, Informatica.

[16]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[17]  Sylvain Leduc,et al.  A quantitative analysis of oil-price shocks, systematic monetary policy, and economic downturns , 2001 .

[18]  Robert P. W. Duin,et al.  K-nearest Neighbors Directed Noise Injection in Multilayer Perceptron Training , 2000, IEEE Trans. Neural Networks Learn. Syst..