Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

Predicting Exchange Rates with Modified Elman Network

수정된 엘만신경망을 이용한 외환 예측

  • Beum-Jo Park (I thank Chung-Min Kuan for his helpful comments and Halbert White and Francis Diebold for their concerns. The remaining errors, of course, of course, are mine. An earlier version of this paper was presented at the Korean Econometric Association Meeting) ;
  • Published : 1997.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper discusses a method of modified Elman network(1990) for nonlinear predictions and its a, pp.ication to forecasting daily exchange rate returns. The method consists of two stages that take advantages of both time domain filter and modified feedback networks. The first stage straightforwardly employs the filtering technique to remove extreme noise. In the second stage neural networks are designed to take the feedback from both hidden-layer units and the deviation of outputs from target values during learning. This combined feedback can be exploited to transfer unconsidered information on errors into the network system and, consequently, would improve predictions. The method a, pp.ars to dominate linear ARMA models and standard dynamic neural networks in one-step-ahead forecasting exchange rate returns.

Keywords

References

  1. Neural Networks in the Capital Markets Financial Market Applications of Learning from Hints Abu-Mostafa, Y.;A. Refenes(ed.)
  2. Technical Report No. 58 Universal Approximation Bounds for Superpositions of a Sigmoidal function Barron, A.
  3. Journal of Business and Economic Statistics v.7 The Message in Daily Exchange Rates : A Conditional Variance Tale Baillie, R.;T. Bollerslev
  4. Crises in the Economic and Financial Structures Bubbles, Rational Expectations and Financial Markets Blanchard, O.;M. Watson;Wachtel, P.(ed.)
  5. Statistical Theory and Economic Evidence Nonlinear Dynamics, Chaos, and Instability Brock, W.;A. Hsieh;B. LeBaron
  6. A Test for Independence Based on the Correlation Dimension Brock, W.;Dechert, W.;J. Scheinkman
  7. Journal of International Money and Finance v.10 Some Linear and Nonlinear Thoughts on Exchange Rates Chinn, M. D.
  8. Empirical Modeling of Exchange Rate Dynamics Diebold, F. X.
  9. Journal of International Economics v.28 Nonparametric Exchange Rate Prediction? Diebold, F.;J. Nason
  10. Cognitive Science v.14 Finding Structure in Time Elman, J.
  11. Econometrica v.50 Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of U.K. Inflation Engle, R.
  12. Neural Networks v.2 On the Approximate Realization of Continuous Mapping by Neural Networks Funahashi, K.I.
  13. Neural Networks v.2 Multi-layer Feedforward Networks Are Universal Approximators Hornik, K.;M. Stinchcombe;H. White
  14. Journal of International Economics The Statistical Properties of Daily Foreign Exchange Rates: 1974-1983 Hsieh, D. A.
  15. Journal of Business v.62 Testing for Nonlinear Dependence in Daily Foreign Exchange Rates Hsieh, D. A.
  16. Neural Networks in the Capital Markets A Neural Network Procedure for Selecting Predictive Indicators in Currency Trading Hsu, W.;L. Hsu;F. Tenorio;A. Refenes(ed.)
  17. NBER Working Paper No 2481 Target Zone and Exchange Rate Dynamics Krugman, P.
  18. BEBR Working Paper, 91-0114 Learning in a Partially Hard-wired Recurrent Network Kuan, C.-M.;K. Hornik
  19. BEBR Working Paper, 92-0128 Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks Kuan, C.-M.;T. Liu
  20. Econometric Reviews v.13 no.1 Artificial Neural Networks: An Econometric Perspective Kuan, C.-M.;H. White
  21. American Economic Review v.80 no.2 Nonlinear, Nonparametric, Nonessential Exchange Rate Estimation Meese, R;A. Rose
  22. Robust Forecasts of Exchange Rates Using Neural Network Regression Quantiles Park, B.-J.
  23. Digital Filter Design Parks, T.;C. Burrus
  24. Parallel Distributed Processing: Explorations in the Microstructure of Cognition Learning Internal Representations by Error Propagation Rumelhart, D.;G. Hinton;R. Williams;Rumelhart(ed.);M. McClelland(ed.)
  25. Explorations in the Microstructures of Cognition Rumelhart, D.;J. McClelland
  26. Biometrika v.73 no.2 Nonlinearity Tests for Time Series Tsay, R. S.
  27. Ph.D. Dissertation, University of Wisconsin-Madison Essays on Nonlinear Models of Foreign Exchange Tsibouris, G.
  28. Intl. J. Neur. Sys. v.1 Predicting the Future: A Connectionist Approach Weigend, A.;B. Huberman;D. Rumelhart
  29. Nonlinear Modeling and Forecasting Predicting Sunspots and Exchange Rates with Connectionist Networks Weigend, A.;M. Casdagli(ed.);S. Eubank(ed.)
  30. Proceedings of the IEEE Second International Conference on Neural Networks v.Ⅱ Economic Prediction Using Neural Networks: The Case of IBM Stock Prices White, H.
  31. A Study in the Analysis of Stationary Time Series Wold, H.
  32. Time Series Prediction: Forecasting the Future and Understanding the Past Simple Architectures on Fast Machines: Practical Issues in Nonlinear Time Series Prediction Zhang, X.;J. Hutchinson;A. Weigend(ed.);N. Gershenfeld