Decision Sciences Journal
Volume 30, Number 1
Winter 1999
A Cross-Validation Analysis of Neural Network Out-of-Sample
Performance in Exchange Rate Forecasting
Michael Y. Hu
Department of Marketing, Kent State University, Kent, OH 44240;
and Department of International Business, Chinese University
of Hong Kong, email: mhu@bsa3.kent.edu
Guoqiang (Peter) Zhang
Department of Decision Sciences, J. Mack Robinson College of
Business, Georgia State University, Atlanta, GA 30303, email:
gpzhang@gsu.edu
Christine X. Jiang and B. Eddy Patuwo
Graduate School of Management, Kent State University, Kent, OH
44240, email: cjiang@bsa3.kent.edu,
epatuwo@bsa3.kent.edu
ABSTRACT. Econometric methods used in foreign exchange
rate forecasting have produced inferior out-of-sample results
compared to a random walk model. Applications of neural networks
have shown mixed findings. In this paper, we investigate the
potentials of neural network models by employing two cross-validation
schemes. The effects of different in-sample time periods and
sample sizes are examined. Out-of-sample performance evaluated
with four criteria across three forecasting horizons shows that
neural networks are a more robust forecasting method than the
random walk model. Moreover, neural network predictions are quite
accurate even when the sample size is relatively small.
Subject Areas: Capital/Asset Pricing, Foreign Exchange
Rates, Neural Networks, and Time Series Forecasting. |