Financial time series prediction using least squares support vector machines within the evidence framework

The Bayesian evidence framework is applied in this paper to least squares support vector machine (LS-SVM) regression in order to infer nonlinear models for predicting a financial time series and the related volatility. On the first level of inference, a statistical framework is related to the LS-SVM formulation which allows one to include the time-varying volatility of the market by an appropriate choice of several hyper-parameters. The hyper-parameters of the model are inferred on the second level of inference. The inferred hyper-parameters, related to the volatility, are used to construct a volatility model within the evidence framework. Model comparison is performed on the third level of inference in order to automatically tune the parameters of the kernel function and to select the relevant inputs. The LS-SVM formulation allows one to derive analytic expressions in the feature space and practical expressions are obtained in the dual space replacing the inner product by the related kernel function using Mercer's theorem. The one step ahead prediction performances obtained on the prediction of the weekly 90-day T-bill rate and the daily DAX30 closing prices show that significant out of sample sign predictions can be made with respect to the Pesaran-Timmerman test statistic.

[1]  Dirk-Emma Baestaens,et al.  Neural Network Solutions for Trading in Financial Markets , 1994 .

[2]  Clive W. J. Granger,et al.  Modelling the Absolute Returns of Different Stock Indices: Exploring the Forecastability of an Alternative Measure of Risk , 1999 .

[3]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[4]  T. Bollerslev,et al.  ANSWERING THE SKEPTICS: YES, STANDARD VOLATILITY MODELS DO PROVIDE ACCURATE FORECASTS* , 1998 .

[5]  A. Neil Burgess,et al.  Neural networks in financial engineering: a study in methodology , 1997, IEEE Trans. Neural Networks.

[6]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[7]  J. Suykens,et al.  Recurrent least squares support vector machines , 2000 .

[8]  Christopher K. I. Williams.  Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond , 1999, Learning in Graphical Models.

[9]  Johan A. K. Suykens,et al.  Nonlinear modeling : advanced black-box techniques , 1998 .

[10]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[11]  Jan G. De Gooijer,et al.  Kernel-based Multistep-ahead Predictions of the US Short-term Interest Rate , 2000 .

[12]  C. Granger,et al.  A long memory property of stock market returns and a new model , 1993 .

[13]  G. Schwert.  Why Does Stock Market Volatility Change Over Time? , 1988 .

[14]  Bernhard Schölkopf,et al.  On a Kernel-Based Method for Pattern Recognition, Regression, Approximation, and Operator Inversion , 1998, Algorithmica.

[15]  Johan A. K. Suykens,et al.  Least squares support vector machines for classification and nonlinear modelling , 2000 .

[16]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[17]  M. Hashem Pesaran,et al.  A Simple Nonparametric Test of Predictive Performance , 1992 .

[18]  R. C. Williamson,et al.  Kernel-dependent support vector error bounds , 1999 .

[19]  C. Granger,et al.  Modelling Nonlinear Economic Relationships , 1995 .

[20]  Johan A. K. Suykens,et al.  Optimal control by least squares support vector machines , 2001, Neural Networks.

[21]  Alexander Gammerman,et al.  Ridge Regression Learning Algorithm in Dual Variables , 1998, ICML.

[22]  Federico Girosi,et al.  An Equivalence Between Sparse Approximation and Support Vector Machines , 1998, Neural Computation.

[23]  Michael D. McKenzie,et al.  Power transformation and forecasting the magnitude of exchange rate changes , 1999 .

[24]  Tomaso A. Poggio,et al.  Regularization Networks and Support Vector Machines , 2000, Adv. Comput. Math..

[25]  Christopher F. Baum,et al.  A nonparametric investigation of the 90-day t-bill rate , 1997 .

[26]  Johan A. K. Suykens,et al.  Volatility Tube Support Vector Machines , 2000 .

[27]  Tim Bollerslev,et al.  Chapter 49 Arch models , 1994 .

[28]  David Mackay,et al.  Probable networks and plausible predictions - a review of practical Bayesian methods for supervised neural networks , 1995 .

[29]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .