RMB Exchange Rate Prediction Based on ARIMA and BP Neural Network Fusion Model

Mingzhu Liao

《World Scientific Research Journal》 6卷4期 (2020/04) Pp. 252-262

https://doi.org/10.6911/WSRJ.202004_6(4).0024

摘要

The data structure of the RMB exchange rate time series can be decomposed into linear and non-linear parts. This paper uses the ARIMA model to predict the linear subject of the series, and then uses the BP neural network model to estimate its nonlinear residuals and fuses together to form a combined model. For the prediction of RMB exchange rate, the research found that the combined model is better than the single model.

關鍵字

RMB exchange rate ； ARIMA ； BP neural network

參考文獻

TH. Hann and E. Steurer (1996).Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data. Neurocomputing, no.10, P.323-339.

MT. Leung, AS. Chen and H. Daouk (2000).Forecasting exchange rates using general regression neural networks. Computers & Operations Research, vol.27, no.11, P.1093-1110.

M. Hibon and T. Evgeniou (2005).To combine or not to combine: selecting among forecasts and their combinations. International Journal of Forecasting, vol.21, no.1, P.15-24.

F.M. Tseng, H.C. Yu and G.H. Tzeng (2002). Combining neural network model with seasonal time series ARIMA model. Technological Forecasting and Social Change, vol.69, no.1, P.71-87.

X.F. Dai and Q.X. Xiao (2005). Time series analysis applied in prediction of RMB’s exchange rate. Journal of University of Shanghai For Science and Technology, vol.27, no.4, P.341-344.