Forecasting Daily and Monthly Exchange Rates with Machine Learning Techniques

Abstract

We combine signal processing to machine learning methodologies by introducing a hybrid Ensemble Empirical Mode Decomposition (EEMD), Multivariate Adaptive Regression Splines (MARS) and Support Vector Regression (SVR) model in order to forecast the monthly and daily Euro (EUR)/United States Dollar (USD), USD/Japanese JPY (JPY), Australian Dollar (AUD)/Norwegian Krone (NOK), New Zealand Dollar (NZD)/Brazilian Real (BRL) and South African Rand (ZAR)/Philippine Peso (PHP) exchange rates. After the decomposition of the original exchange rate series with EEMD into a smoothed and a fluctuation component, MARS selects the most informative from the plethora of variables included in our initial data set. The selected variables are fed into two distinctive SVR models for forecasting each component separately one period ahead with the summation providing exchange rate forecasts. The above implementation exhibits superior forecasting ability in exchange rate forecasting and high Sharpe Ratios compared to various models taking data snooping bias in consideration, rejecting the Efficient Market Hypothesis for all foreign exchange markets. Overall the proposed model a) is a combination of empirically proven effective techniques in forecasting time series, b) is data driven, c) relies on minimum initial assumptions and d) provides a structural aspect of the forecasting problem.