Time Series Prediction Based on Multiple Artificial Neural Network

Time series prediction is a challenging research area with broad application prospects. Accurate time series prediction can provide important information for the relevant decision-makers. Many works extended different architecture of artificial neural networks to work with time series prediction, but they mostly only consider the time series itself, does not weigh the impact of relevant time series. In this paper we proposed a method of utilizing multiple artificial neural networks to conduct the time series prediction, create time series model and forecast time series. We apply the proposed method for a shipping price index time series prediction, experimental results show that this method can improve accuracy of prediction when compared with traditional methods.