This paper models the return series of USD/CNY exchange rate by considering the conditional mean and conditional volatility simultaneously. An index type functional-coefficient model is adopted to model the conditional mean part and a GARCH type model with a policy dummy variable is applied to the conditional volatility model. We show that the government policy indeed has an impact on the exchange rate dynamic. To evaluate the out-of-sample forecasting ability, a prediction interval is computed by employing nonparametric conditional quantile regression. Our method outperforms other popular models in terms of various criteria.