Establishment of Shipping Container Price Prediction Model for International Trade

In order to more accurately grasp the fluctuation trend of container transportation freight in international trade, a prediction model of China Containerized Freight Index (CCFI) based on empirical mode decomposition (EMD) and BP neural network was proposed. Firstly, EMD was selected to decompose and reconstruct the freight index, and then BP neural network was utilized to predict the freight index. The results showed that compared with EMD-ARIMA prediction model, the EMD-BP neural network prediction model has a better fitting effect, and the predicted value coincides with the true value better. Compared with other models such as EMD-ARIMA, the prediction model based on EMD-BP constructed in this paper shows better prediction performance on root mean squared error (RMSE) and other indicators, and the accuracy of the prediction direction reaches 0.8623. By predicting CCFI freight index, the future freight changes of international trade can be better grasped, so as to obtain the superiority of EMD-BP prediction model proposed in this paper, which has certain engineering application value in the field of international trade.