Why is it so difficult to beat the random walk forecast of exchange rates?

We propose a nonlinear econometric model that can explain both the observed volatility and the persistence of real and nominal exchange rates. The model implies that near equilibrium, the nominal exchange rate will be well approximated by a random walk process. Large departures from fundamentals, in contrast, imply mean-reverting behavior toward fundamentals. Moreover, the predictability of the nominal exchange rate relative to the random walk benchmark tends to improve at longer horizons. We test the implications of the model and find strong evidence of exchange rate predictability at horizons of two to three years, but not at shorter horizons