Multivariate Time Series Modelling of Financial Markets with Artificial Neural Networks

  • Thomas Ankenbrand
  • Marco Tomassini


This work presents an integrated approach for modelling the behaviour of financial markets with Artificial Neural Networks (ANNs). The model allows to forecast financial time series. Its originality lies in the fact that it is based on statistics and macroeconomics principles and it integrates fundamental economic knowledge in a multivariate nonlinear time series ANN model. The model is applied to real-life case studies and the results are discussed.


Interest Rate Financial Market Stock Index Hurst Exponent Feasibility Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Peters, E.E.: Chaos and Order in the Capital Markets. John Wiley & Sons, 1991, 165.Google Scholar
  2. 2.
    Klimasauskas, C.C.: Neural Network Techniques. In Deboeck, G.J. (Ed.): Trading on the Edge. John Wiley & Sons, 1994, 13f.Google Scholar
  3. 3.
    Peters, E.E.: Fractal Market Analysis. John Wiley & Sons, 1994, 56ff..Google Scholar
  4. 4.
    Lee, T.-H., White, H., Granger, W.J.: Testing for neglected nonlinearity in time series models. In Journal of Econometrics. Elsevier Science Publishers, 1993, 269ff..Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Thomas Ankenbrand
    • 1
  • Marco Tomassini
    • 2
    • 3
  1. 1.Institut d’Informatique Faculté des SciencesUniversity of LausanneSwitzerland
  2. 2.Swiss Centre of Scientific ComputingMannoSwitzerland
  3. 3.Laboratoire de Systèmes Logiques, Departement d’InformatiqueEcole Polytechnique Fédérale de LausanneSwitzerland

Personalised recommendations