RMB Exchange Rate Forecasting in the Context of the Financial Crisis

Abstract

Abstract This article offers an effective solution of forecasting the RMB exchange rate volatility during the financial crisis period. Based on the test of nonlinearity structure in the exchange rate system via the method of surrogate data, the optimal lag periods for each specific exchange rate series were computed by autocorrelation criterion (AC) approach, and then, the structure of multilayer perceptrons (MLP) and recurrent neural networks (RNN) were applied to build the homogeneous artificial neural network (ANN) model. The comparison of the forecast results of ANNs with different parameters shows that, according to the specific exchange rate series, the forecast performance of ANN models with different freedom of degrees has obvious differences in different forecast periods. The RNN model, which contains layer feedback process, has showed great ability to explain and forecast the RMB exchange rates volatility behavior. The optimal forecasting model for each RMB exchange rate volatility series has been found and explained.