Forecasting chaotic time series with a hybrid model
Fan Chong-jun · Science-technology and Management · 2012
The combination of neural network and the traditional linear model provides a new way to deal with chaotic time series.This paper proposes a hybrid autoregressive integrated moving average(ARIMA) and Elman's recurrent neural networks(ERNN) model to forecast international trade time series.The results show that the proposed model has more forecasting accuracy than that of single model.