Neural ARFIMA model for forecasting BRIC exchange rates with long memory under oil shocks and policy uncertainties.
Under Review., 2026
Forecasting exchange rates in emerging economies is challenging due to long memory, nonlinearity, non-stationarity, and the influence of key global and domestic drivers. In this work, we propose NARFIMA, a hybrid framework that integrates ARFIMA with neural networks while incorporating exogenous variables. The model captures complex dynamics and provides theoretical guarantees, including asymptotic stationarity.
