Skip to main content

Forecasting time series with connectionist nets: Applications in statistics, signal processing and economics

  • Finance
  • Conference paper
  • First Online:
Industrial and Engineering Applications of Artificial Intelligence and Expert Systems (IEA/AIE 1992)

Abstract

Although these first results are quite surprising they are still not more than preliminary. The quality of the modelling in our case studies motivates further research in this area. We are quite far from a real understanding time series analysis with connectionist networks. Many parameters have to be adjusted—they should be derived from the data to be analysed rather than from empirical analysis of the nets' behaviour. The lack of robustness also is a serious problem.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. D.E. Rumelhart and J.L. McClelland, Parallel Distributed Processing, Explorations in the Micro structure of Cognition, Vols. 1&2, MIT Press, Cambridge 1987.

    Google Scholar 

  2. G. Cybenko, Techn. Rep. No. 856, Urbana Univ. of Illinois, 1988

    Google Scholar 

  3. K.-I. Funahashi, Neural Networks 2, 189, 1989

    Article  Google Scholar 

  4. K. Hornik, M. Stinchcombe and H. White, Neural Networks 2, 359, 1989.

    Article  Google Scholar 

  5. A. Lapades, LA-ÜR87-226 Los Alamos Report, 1987.

    Google Scholar 

  6. G.E.P. Box and G.M. Jenkins, Time Series Analysis, Forecasting and Control, Holden-Day, San Francisco 1970.

    Google Scholar 

  7. T.W. Anderson, The Statistical Analysis of Time Series, Wiley, New York 1971

    Google Scholar 

  8. M.B. Priestley, Spectral Analysis and Time Series, Academic Press, London 1981

    Google Scholar 

  9. C.W.J. Granger and P. Newbold, Forecasting Economic Time Series, Academic Press, New York 1986.

    Google Scholar 

  10. C.W.J. Granger and T.W. Anderson, An Introduction to Bilinear Time Series Models, Vandenhoeck and Ruprecht, Göttingen 1978

    Google Scholar 

  11. T. Subba Rao and M.M. Gabr, An Introduction to Bispectral Analysis and Bilinear Time Series Models, Lecture Notes in Statistics Vol. 24, Springer, Berlin 1984

    Google Scholar 

  12. H. Tong, Non-linear Time Series, University Press, Oxford 1990

    Google Scholar 

  13. T. Ozaki, Nonlinear Time Series Models and Dynamical Systems, in: Handbook of Statistics, (E.J. Hannan et al., eds.) Vol. 5, North-Holland, Amsterdam 1985

    Google Scholar 

  14. M.B. Priestley, Non-linear and Non-stationary Time Series Analysis, Academic Press, London 1988.

    Google Scholar 

  15. C. de Groot and D. Würtz, Analysis of Univariate Time Series with Connectionist Nets, Proceedings of the Munotec Workshop, Dublin 1990 and Neurocomputing (in press), 1991

    Google Scholar 

  16. C. de Groot and D. Würtz, Signal Processing and Noise Reduction with Connectionist Networks, Helvetica Physica Acta (in press), 1991

    Google Scholar 

  17. Würtz and C. de Groot, Dollarprognose, unpublished results, IPS Zürich 1991.

    Google Scholar 

  18. A.J. Izenman, Math. Intelligencer 7, 27, 1985.

    Google Scholar 

  19. G.U. Yule, Phil. Trans. Royal Soc. London A226, 267, 1927.

    Google Scholar 

  20. P.A.P. Moran, J. Royal Stat. Soc. B16, 112, 1954

    Google Scholar 

  21. M.C. Schaerf, Technical Report, Department of Statistics, Stanford 1964

    Google Scholar 

  22. M.J. Morris, J. Royal Stat. Soc. A140, 437, 1977

    Google Scholar 

  23. P. Hokstad, J. Time Series An. 4, 177, 1983.

    Google Scholar 

  24. M.M. Gabr and T. Subba Rao, J. Time Series An. 2, 155, 1981.

    Google Scholar 

  25. H. Tong and K.S. Lim, J. Royal Stat. Soc. B42, 245, 1980.

    Google Scholar 

  26. A.S. Weigend and D.E. Rumelhart, Proceedings of Interface '91, Springer Verlag (in press) 1991

    Google Scholar 

  27. A.S. Weigend, B.A. Huberman and D.E. Rumelhart, Santa Fe Workshop 1990, NATO Workshop Proceedings, Addison Wesley (in press) 1991.

    Google Scholar 

  28. Y. Sakamoto and M. Ishiguro, Akaike Information Criterion Statistics, Reidel Publishing, Dordrecht 1986.

    Google Scholar 

  29. E.W. Heri, Finanzmarkt und Portfoliomanagement 1, 47, 1986/87

    Google Scholar 

  30. E.W. Heri, Revista Int. di Scienze Economiche e Commerciali 33, 1057, 1986.

    Google Scholar 

  31. C. de Groot and D. Würtz, Proceedings of the IUTAM Workshop, Warwick, 1991, to appear in Physica D.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Fevzi Belli Franz Josef Radermacher

Rights and permissions

Reprints and permissions

Copyright information

© 1992 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

de Groot, C., Würtz, D. (1992). Forecasting time series with connectionist nets: Applications in statistics, signal processing and economics. In: Belli, F., Radermacher, F.J. (eds) Industrial and Engineering Applications of Artificial Intelligence and Expert Systems. IEA/AIE 1992. Lecture Notes in Computer Science, vol 604. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0024998

Download citation

  • DOI: https://doi.org/10.1007/BFb0024998

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-55601-5

  • Online ISBN: 978-3-540-47251-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics