RMB/USD Exchange Rate Forecasting and Analysis by SES and ARIMA Model

Abstract

The RMB/USD exchange rate is important in the worldwide financial sector. Predicting the future RMB/USD exchange rate is critical in such circumstances. Forecasting the RMB/USD exchange rate effectively can assist people in analyzing the economic situation and avoiding financial dangers. This research proposes two statistical models, Simple Exponential Smoothing (SES) model and Autoregressive Integrated Moving (ARIMA) model, for forecasting the RMB/USD exchange rate, and then discovers a better model for forecasting exchange rates. To find a better model, forecast value with accuracy, and uncertainty and model limitation are compared. We find that although SES model shows a better accuracy, the residual check and uncertainty shows ARIMA is a better forecast. Moreover, ARIMA is more complex and has relatively less limitations for RMB/USD exchange rate. Thus, Autoregressive Integrated Moving model is a better forecast compared with Simple Exponential Smoothing model.