Forecasting exchange rates using general regression neural networks Mark T. Leung *, An-Sing Chen , Hazem Daouk
Division of Management and Marketing, College of Business, University of Texas at San Antonio, San Antonio, TX 78249, USA Department of Finance, National Chung Cheng University, Ming Hsiung, Chia Yi 612, Taiwan, ROC Department of Finance, Kelley School of Business, Indiana University, Bloomington, IN 47405, USA
Abstract In this study, we examine the forecastability of a speci"c neural network architecture called general regression neural network (GRNN) and compare its performance with a variety of forecasting techniques, including multi-layered feedforward network (MLFN), multivariate transfer function, and random walk models. The comparison with MLFN provides a measure of GRNN's performance relative to the more conventional type of neural networks while the comparison with transfer function models examines the di!erence in predictive strength between the non-parametric and parametric techniques. The di$cult to beat random walk model is used for benchmark comparison. Our "ndings show that GRNN not only has a higher degree of forecasting accuracy but also performs statistically better than other evaluated models for di!erent currencies. Scope and purpose Predicting currency movements has always been a problematic task as most conventional econometric models are not able to forecast exchange rates with signi"cantly higher accuracy than a naive random walk model. For large multinational "rms which conduct substantial currency transfers in the course of business, being able to accurately forecast the movements of exchange rates can result in considerable improvement in the overall pro"tability of the "rm. In this study, we apply the general regression neural network (GRNN) to predict the monthly exchange rates of three currencies, British pound, Canadian dollar, and Japanese yen. Our empirical experiment shows that the performance of GRNN is better than other neural network and econometric techniques included in this study. The results demonstrate the predictive strength of GRNN and its potential for solving "nancial forecasting problems. 2000 Elsevier Science Ltd. All rights reserved. Keywords: General regression neural networks; Currency exchange rate; Forecasting
* Corresponding author. Tel.: #1-210-458-5776; fax: #1-210-458-5783. E-mail addresses: email@example.com (M.T. Leung), "firstname.lastname@example.org (A.-S. Chen), email@example.com (H. Daouk) 0305-0548/00/$ - see front matter 2000 Elsevier Science Ltd. All rights reserved. PII: S 0 3 0 5 - 0 5 4 8 ( 9 9 ) 0 0 1 4 4 - 6
M.T. Leung et al. / Computers & Operations Research 27 (2000) 1093}1110
1. Introduction Applying quantitative methods for forecasting in "nancial markets and assisting investment decision making has become more indispensable in business practices than ever before. For large multinational "rms which conduct substantial currency transfers in the course of business, being able to accurately forecast movements of currency exchange rates can result in substantial improvement in the overall pro"tability of the "rm. Nevertheless, predicting exchange rate movements is still a problematic task. Most conventional econometric models are not able to forecast exchange rates with signi"cantly higher accuracy than a naive random walk model. In recent years, there has been a growing interest to adopt the state-of-the-art arti"cial intelligence technologies to solve the problem. One stream of these advanced techniques focuses on the use of arti"cial neural networks (ANN) to analyze the historical data and provide predictions to future movements in the foreign exchange market. In this study, we apply a special class of neural networks, called general regression neural network (GRNN), to forecast the monthly exchange rates for three internationally traded currencies, Canadian dollar,...