Predicting returns on Canadian exchange rates with artificial neural networks and EGARCH-M models

This paper investigates the problem of predicting daily returns based on five Canadian exchange rates using artificial neural networks and EGARCH-M models. First, the statistical properties of five daily exchange rate series (US Dollar, German Mark, French Franc, Japanese Yen and British Pound) are analysed. EGARCH-M models on the Generalised Error Distribution (GED) are fitted to the return series, and serve as comparison standards, along with random walk models. Second, backpropagation networks (BPN) using lagged returns as inputs are trained and tested. Estimated volatilities from the EGARCH-M models are used also as inputs to see if performance is affected. The question of spillovers in interrelated markets is investigated with networks of multiple inputs and outputs. In addition, Elman-type recurrent networks are also trained and tested. Comparison of the various methods suggests that, despite their simplicity, neural networks are similar to the EGARCH-M class of nonlinear models, but superior to random walk models, in terms of insample fit and out-of-sample prediction performance.

[1]  Douglas M. Patterson,et al.  Nonlinear Dynamics, Chaos, And Instability , 1994 .

[2]  R. Baillie,et al.  The Message in Daily Exchange Rates , 1989 .

[3]  Kenneth A. Froot,et al.  Stochastic Process Switching: Some Simple Solutions , 1989 .

[4]  Anil K. Bera,et al.  ARCH Models: Properties, Estimation and Testing , 1993 .

[5]  Achilleas Zapranis,et al.  Stock performance modeling using neural networks: A comparative study with regression models , 1994, Neural Networks.

[6]  Thomas Kolarik,et al.  Time series forecasting using neural networks , 1994, APL '94.

[7]  Apostolos Nikolaos Refenes,et al.  Currency exchange rate prediction and neural network design strategies , 1993, Neural Computing & Applications.

[8]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[9]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[10]  Ronald W. Masulis,et al.  Correlations in Price Changes and Volatility Across International Stock Markets , 1990 .

[11]  T. Bollerslev,et al.  Modelling the Coherence in Short-run Nominal Exchange Rates: A Multivariate Generalized ARCH Model , 1990 .

[12]  Chung-Ming Kuan,et al.  Forecasting exchange rates using feedforward and recurrent neural networks , 1992 .

[13]  Paul A. Fishwick,et al.  Time series forecasting using neural networks vs. Box- Jenkins methodology , 1991, Simul..

[14]  Panayiotis Theodossiou,et al.  The Stochastic Properties of Major Canadian Exchange Rates , 1994 .

[15]  David A. Hsieh,et al.  Modeling Heteroscedasticity in Daily Foreign-Exchange Rates , 1989 .

[16]  Hong Pi.  Dependency Analysis and Neural Network Modeling of Currency Exchange Rates , 1993 .

[17]  Craig S. Hakkio,et al.  Conditional variance and the risk premium in the foreign exchange market , 1985 .

[18]  Halbert White,et al.  Artificial Neural Networks: Approximation and Learning Theory , 1992 .

[19]  A. Gallant,et al.  On Fitting A Recalcitrant Series: The Pound/Dollar Exchange Rate, 1974- 83 , 1988 .

[20]  Patrick Minford,et al.  The Foreign Exchange Market: Theory and Econometric Evidence , 1990 .

[21]  H. White,et al.  Economic prediction using neural networks: the case of IBM daily stock returns , 1988, IEEE 1988 International Conference on Neural Networks.