A Flexible Kernel Regression Decomposition-Based Hybrid Framework for Forecasting Foreign Exchange Rates: Uncovering Symmetric and Asymmetric Market Dynamics

Abstract

Foreign exchange rate forecasting is difficult, as its time series have complex nonlinear and nonstationary dynamics. To this end, the paper proposes a hybrid forecasting framework based on kernel regression decomposition that combines nonparametric trend extraction with linear and nonlinear forecasting models. In the framework we propose, we decompose each series of exchange rates into a long-run trend component and a short-run fluctuation component, which are modeled separately and then combined to generate forecasts. An empirical study based on five major foreign exchange markets shows that the proposed framework consistently outperforms conventional hybrid and standalone forecasting models in multiple forecasting accuracy measures. The statistical validation of the forecasting improvements is confirmed by the Diebold–Mariano test. Moreover, the decomposition offers an interpretable representation of exchange-rate dynamics by distilling persistent long-run movements from localized short-run nonlinear fluctuations. The results indicate that the proposed framework improves forecasting accuracy and offers insight into the structural behavior of foreign exchange markets.