IMPROVING ICA ALGORITHMS APPLIED TO PREDICTING STOCK RETURNS

J. M. Górriz, C. G. Puntonet, R. Martín-Clemente

2004

Abstract

In this paper we improve a well known signal processing technique such as independent component analysis (ICA) or blind source separation applied to predicting multivariate financial such as portfolio of stock returns using the Vapnik-Chervonenkis theory. The key idea in ICA algorithms is to linearly map the input space series (stock returns) into a new space which contains statistically independent components. There´s a wide class of ICA algorithms however they usually fail due to their high convergence rates or their limited ability of local search, as the number of observed signals increases.

References

  1. Back, A. and Weigend, A. (1997). A first application of independent component analysis to extracting structure from stock returns. International Journal of Neural Systems, vol. 8(5).
  2. Bell, A. and Sejnowski, T. (1995). An informationmaximization approach to blind separation and blind deconvolution. Neural Computation, vol. 7:1129- 1159.
  3. Cao, X. and Liu, W. (1996). General approach to blind source separation. In IEEE Transactions on signal Processing, volume vol. 44,3, pages 562-571.
  4. Eiben, A., Aarts, E., and Hee, K. V. (1991). Global convergence of genetic algorithms:a markov chain analysis. Parallel Problem Solving from Nature, Lecture Notes in Computer Science, vol. 496:4-12.
  5. Górriz, J. M., Puntonet, C. G., Salmerón, M., and Ortega, J. (June 2003). New method for filtered ica signals applied to volatile time series. Lecture Notes in Computer Science, LNCS, vol. 2687:433-440,ISSN 0302- 9743.
  6. Górriz, J., Puntonet, C., and Salmerón, M. (2004). On line algorithm for time series prediction based on support vector machine philosophy. In The International Conference on Computational Science. Lecture notes on Computer Science. ICCS 2004, Krakow, Poland USA.
  7. Hyvärinen, A. and Oja, E. A fast fixed point algorithm for independent component analysis. Neural Computation, 9:1483-1492.
  8. Muller, K., Smola, A., Ratsch, G., Scholkopf, B., and Kohlmorgen, J. (1999). Using support vector machines for time series prediction. Advances in kernel Methods-Support Vector Learning, MIT Press, pages 243-254.
  9. Platt, J. (1991). A resource-allocating network for function interpolation. Neural Computation, 3:213-225.
  10. Salmerón-Campos, M. (2001). Predicción de Series Temporales con Rede Neuronales de Funciones Radiales y Técnicas de Descomposición Matricial. Phd thesis, University of Granada, Departamento de Arquitectura y Tecnología de Computadores.
  11. Smola, A., Scholkopf, B., and Muller, K. The connection between regularization operators and support vector kernels. Neural Networks, 11:637-649.
  12. Tan, Y. and Wang, J. (2001). Nonlinear blind source separation using higher order statistics and a genetic algorithm. IEEE Transactions on Evolutionary Computation, vol. 5(6).
  13. Vapnik, V. (1999). The Nature of Statistical Learning Theory. Springer, 2nd edition edition.
Download


Paper Citation


in Harvard Style

M. Górriz J., G. Puntonet C. and Martín-Clemente R. (2004). IMPROVING ICA ALGORITHMS APPLIED TO PREDICTING STOCK RETURNS . In Proceedings of the First International Conference on E-Business and Telecommunication Networks - Volume 3: ICETE, ISBN 972-8865-15-5, pages 351-355. DOI: 10.5220/0001399803510355


in Bibtex Style

@conference{icete04,
author={J. M. Górriz and C. G. Puntonet and R. Martín-Clemente},
title={IMPROVING ICA ALGORITHMS APPLIED TO PREDICTING STOCK RETURNS},
booktitle={Proceedings of the First International Conference on E-Business and Telecommunication Networks - Volume 3: ICETE,},
year={2004},
pages={351-355},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001399803510355},
isbn={972-8865-15-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on E-Business and Telecommunication Networks - Volume 3: ICETE,
TI - IMPROVING ICA ALGORITHMS APPLIED TO PREDICTING STOCK RETURNS
SN - 972-8865-15-5
AU - M. Górriz J.
AU - G. Puntonet C.
AU - Martín-Clemente R.
PY - 2004
SP - 351
EP - 355
DO - 10.5220/0001399803510355