Forecasting exchange rates using neural networks: A trader's approach

Abstract

This study is to investigate the use of Artificial Neural Networks (ANN) for
forecasting exchange rates. The currencies examined in the paper are the Euro, Pound,
and Yen. Two different types of ANNs are used in this paper: Feedforward and
Nonlinear Autoregressive with Exogenous Input (NARX). Forecasts are made for daily
and weekly exchange rates using the open, high, low, and close of the exchange rates.
Many standard econometric models cannot deal with daily and weekly forecasts due
to many macro economic variables not being available at such frequencies. ANNs are
able to deal with daily and weekly data as well as the nonlinearities in exchange rate
movements.

Date of Award	2011
Original language	American English
Awarding Institution	Eastern Illinois University
Supervisor	Ahmed Abou-Zaid (Supervisor)