Exchange Rate Prediction Using Support Vector Machines: a Comparison with Artificial Neural Networks

With an estimated $4.0 trillion average daily turnover, the global foreign currency exchange market is undoubtedly considered the largest and most liquid of all financial markets. The exchange market is a complex, nonlinear, and a dynamic system of which its time series, represented by the exchange rates, are inherently noisy, non-stationary, non-linear, and of an unstructured nature. These characteristics, combined with the immense trading volume and the many correlated influencing factors of economic, political, and psychological nature, has made exchange rate prediction one of the most difficult and demanding applications of financial forecasting, and an issue of much interest to both academic and economic communities. Being able to accurately forecast exchange rate movements provides considerable benefits to both firms and investors. This research aims to propose a decision support aid to these firms and investors, enabling them to better anticipate on possible future exchange rate movements, based on one of the most promising prediction models recently developed within computational intelligence: the Support Vector Machine.