Abstract
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.
Similar content being viewed by others
References
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.
Baily, D. and Thompson, D.M. (1990), ‘Developing Neural Network Applications’.AI Expert. September, 33–41.
Blum, A. (1992),Neural Networks in C++: An Object Oriented Framework for Building Connectionist Systems. John Wiley and Sons, Inc.
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.
Caudill, M. (1992), ‘The view from Now’.AI Expert, June, 24–31.
Caudill, M. and Butler, C. (1992),Understanding Neural Networks: Computer Applications, MIT Press, Cambridge, MA.
Cavanaugh, K.L. (1987), ‘Price Dynamics in Foreign Currency Future Markets’.Journal of International Money and Finance,6, 295–314.
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.
Chong, M. and Fallside, F. (1988), ‘Implementation of Neural Networks for Speech Recognition on a Transputer Array’. Cambridge University, Department of Engineering. March.
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.
Fama, E.F. (1991), ‘Efficient Capital Markets: IIJournal of Finance,46, 1575–1617.
Hecht-Nielsen, R. (1988), ‘Neurocomputing: Picking the Human Brain’.IEEE Spectrum, March.
Hornik, K., Stinchcombe, M. and White, M. (1989), ‘multilayer Feedforward Networks are Universal Approximators’.Neural Networks,2, 359–66.
Hsieh, D.A. (1989), ‘Testing for Nonlinear Dependence in Daily Foreign Exchange Rates’.Journal of Business,62, 339–68.
Kao, G. and Ma, C. (1992), ‘Memories, Heteroscedasticity and Prices Limit Currency Futures Markets’.The Journal of Futures Markets,12, 679–92.
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.
Malkiel, B.G. (1981),A Random Walk Down on Wall Street, Norton.
Masters, T. (1993),Practical Neural Network Recipe in C + +., Academic Press, Inc.
McClelland, J.L. and Rumelhart, D.E. (1981),Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercise, Cambridge, MIT Press.
McCullock, W. and Pitts, W (1943), ‘A Logical Calculus of the Ideas Immanent in Nervous Activity’.Bulletin of Mathematical Biophysics 5, 115–133.
Minsky, M. and Papert, S. (1969), Perceptrons. Cambridge, MA: MIT Press.
Nelson, M.M. and Illingworth, W.T. (1991),A Practical Guide to Neural Nets, Addison Wesley Publishing.
Neuroshell 2. (1993),User's Manual, Ward Systems Group, Fredricksburg, MD.
Peters, E.E. (1991),Chaos and Order in The Capital Markets, John Wiley Publishing.
Peters, E.E. (1994),Fractal Market Analysis, John Wiley Publishing.
Peterson, R., Ma, C. and Richey, R. (1992), ‘Dependence in Commodity Prices’.Journals of Futures Markets,12, 428–446.
Rumelhart, D.J., McClelland and the PDP Group (1986), ‘Parallel Distributed Processing’.Explorations in the Microstructure of Cognition, Vol. 1: Foundation, Cambridge, MIT Press.
Author information
Authors and Affiliations
Additional information
The author wish to thank the reviewers Drs. Kraft and Radford for their helpful comments.
Rights and permissions
About this article
Cite this article
Dematos, G., Boyd, M.S., Kermanshahi, B. et al. Feedforward versus recurrent neural networks for forecasting monthly japanese yen exchange rates. Financial Engineering and the Japanese Markets 3, 59–75 (1996). https://doi.org/10.1007/BF00868008
Issue Date:
DOI: https://doi.org/10.1007/BF00868008