2012 Distinguished Master's Thesis Award Winner
Adam Stokes, Master of Arts in Economics, earned EIU's top research honor for his master's thesis titled, Forecasting Foreign Exchange Rates Using Artificial Neural Networks: A Trader’s Approach. Ahmed Abou-Zaid, Ph.D., assistant professor of economics, served as faculty mentor.
Thesis Abstract
This Thesis is an attempt to forecast the foreign exchange rate of three major currencies: The Euro, the Yen, and the British pound against the U.S. Dollar, for trading purposes. The use of traditional techniques such as Autoregressive (AR), Moving Average (MA), or Autoregressive Integrated Moving Average (ARIMA) have major shortcomings notably related to the accuracy of the predicted values. This research paper, thus, utilizes a fairly new technique, which is Artificial Neural Networks (ANNs), which are powerful when applied to problems whose solutions require complex relationships. It also has an advantage over standard models in that they do not require a specified functional relationship between the input and output variables. The results from the neural network model exhibited that using technical indicators as input values can lead to significant market timing ability. The two neural network types, used in the exchange rate forecasting, proved to be forecasting at a higher accuracy (sign prediction) than random walk or ARMA models discussed in the literature.
