Feedforward versus recurrent neural networks for forecasting monthly japanese yen exchange rates

  • Giovani Dematos
  • Milton S. Boyd
  • Bahman Kermanshahi
  • Nowrouz Kohzadi
  • Iebeling Kaastra


Neural networks are a relatively new computer artificial intelligence method which attempt to mimic the brain's problem solving process and can be used for predicting nonlinear economic time series. Neural networks are used to look for patterns in data, learn these patterns, and then classify new patterns and make forecasts. Feedforward neural networks pass the data forward from input to output, while recurrent networks have a feedback loop where data can be fed back into the input at some point before it is fed forward again for further processing and final output. Some have argued that since time series data may have autocorrelation or time dependence, the recurrent neural network models which take advantage of time dependence may be useful. Feedforward and recurrent neural networks are used for comparison in forecasting the Japanese yen/US dollar exchange rate. A traditional ARIMA model is used as a benchmark for comparison with the neural network models.

Results for out of sample show that the feedforward model is relatively accurate in forecasting both price levels and price direction, despite being quite simple and easy to use. However, the recurrent network forecast performance was lower than that of the feedforward model. This may be because feed forward models must pass the data from back to forward as well as forward to back, and can sometimes become confused or unstable. Both the feedforward and recurrent models performed better than the ARIMA benchmark model.

Key words

feedforward neural networks recurrent neural networks ARIMA forecast Japanese yen/US dollar exchange rate 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aikaike, H. (176), ‘Canonical Correlations Analysis of Times Series and the use of an Information Criterion’. In R. Mehra and D.G. Lainiotis (eds.)Advances and Case Studies in System Identification, Academic Press.Google Scholar
  2. 2.
    Baily, D. and Thompson, D.M. (1990), ‘Developing Neural Network Applications’.AI Expert. September, 33–41.Google Scholar
  3. 3.
    Blum, A. (1992),Neural Networks in C++: An Object Oriented Framework for Building Connectionist Systems. John Wiley and Sons, Inc.Google Scholar
  4. 4.
    Bowen, J.E. (1991), ‘Using Neural Network Nets to redict Several Sequential and Subsequent Future Values from Time Series Data’.The First International Conference on Artificial Intelligence Applications on Wall Street, IEEE, 30–34.Google Scholar
  5. 5.
    Caudill, M. (1992), ‘The view from Now’.AI Expert, June, 24–31.Google Scholar
  6. 6.
    Caudill, M. and Butler, C. (1992),Understanding Neural Networks: Computer Applications, MIT Press, Cambridge, MA.Google Scholar
  7. 7.
    Cavanaugh, K.L. (1987), ‘Price Dynamics in Foreign Currency Future Markets’.Journal of International Money and Finance,6, 295–314.Google Scholar
  8. 8.
    Chakraborty, K., Mehrotra, K., Mohan, C.K. and Ranka, S. (1992), ‘Forecasting the Behavior of Multivariate Time Series Using Neural Networks’.Neural Networks,5, 961–970.Google Scholar
  9. 9.
    Chong, M. and Fallside, F. (1988), ‘Implementation of Neural Networks for Speech Recognition on a Transputer Array’. Cambridge University, Department of Engineering. March.Google Scholar
  10. 10.
    Cumby, R.E. and Modest, D.M. (1987), ‘Testing for Market Timing Ability: A Framework for Forecast Evaluation’.Journal of Financial Economics,19, 169–189.Google Scholar
  11. 11.
    Fama, E.F. (1991), ‘Efficient Capital Markets: IIJournal of Finance,46, 1575–1617.Google Scholar
  12. 12.
    Hecht-Nielsen, R. (1988), ‘Neurocomputing: Picking the Human Brain’.IEEE Spectrum, March.Google Scholar
  13. 13.
    Hornik, K., Stinchcombe, M. and White, M. (1989), ‘multilayer Feedforward Networks are Universal Approximators’.Neural Networks,2, 359–66.CrossRefGoogle Scholar
  14. 14.
    Hsieh, D.A. (1989), ‘Testing for Nonlinear Dependence in Daily Foreign Exchange Rates’.Journal of Business,62, 339–68.Google Scholar
  15. 15.
    Kao, G. and Ma, C. (1992), ‘Memories, Heteroscedasticity and Prices Limit Currency Futures Markets’.The Journal of Futures Markets,12, 679–92.Google Scholar
  16. 16.
    Levich, R.M. and Thomas, L.R. (1993), ‘The Significance of Technical Trading Rule Profits in the Foreign Exchange Market: A Bootstrap Approach’.Strategic Currency Investing — Trading and Hedging in the Foreign Exchange Market, Probus Publishing Company, 336-65.Google Scholar
  17. 17.
    Malkiel, B.G. (1981),A Random Walk Down on Wall Street, Norton.Google Scholar
  18. 18.
    Masters, T. (1993),Practical Neural Network Recipe in C + +., Academic Press, Inc.Google Scholar
  19. 19.
    McClelland, J.L. and Rumelhart, D.E. (1981),Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercise, Cambridge, MIT Press.Google Scholar
  20. 20.
    McCullock, W. and Pitts, W (1943), ‘A Logical Calculus of the Ideas Immanent in Nervous Activity’.Bulletin of Mathematical Biophysics 5, 115–133.Google Scholar
  21. 21.
    Minsky, M. and Papert, S. (1969), Perceptrons. Cambridge, MA: MIT Press.Google Scholar
  22. 22.
    Nelson, M.M. and Illingworth, W.T. (1991),A Practical Guide to Neural Nets, Addison Wesley Publishing.Google Scholar
  23. 23.
    Neuroshell 2. (1993),User's Manual, Ward Systems Group, Fredricksburg, MD.Google Scholar
  24. 24.
    Peters, E.E. (1991),Chaos and Order in The Capital Markets, John Wiley Publishing.Google Scholar
  25. 25.
    Peters, E.E. (1994),Fractal Market Analysis, John Wiley Publishing.Google Scholar
  26. 26.
    Peterson, R., Ma, C. and Richey, R. (1992), ‘Dependence in Commodity Prices’.Journals of Futures Markets,12, 428–446.Google Scholar
  27. 27.
    Rumelhart, D.J., McClelland and the PDP Group (1986), ‘Parallel Distributed Processing’.Explorations in the Microstructure of Cognition, Vol. 1: Foundation, Cambridge, MIT Press.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Giovani Dematos
    • 1
  • Milton S. Boyd
    • 2
  • Bahman Kermanshahi
    • 3
  • Nowrouz Kohzadi
    • 4
  • Iebeling Kaastra
    • 5
  1. 1.ABN-AMRO BankSao PauloBrazil
  2. 2.University of ManitobaWinnipegCanada
  3. 3.Tokyo Metropolitan UniversityTokyoJapan
  4. 4.Export Development Bank of IranTehranIran
  5. 5.Canadian Wheat BoardWinnipegCanada

Personalised recommendations