Prediction model of port throughput based on game theory and multimedia Bayesian regression

摘要

In order to simulate the situation of freight flow in overlapping hinterland, we forecast the throughput of port and introduce the game theory to improve it. On the basis of this, a multimedia Bayesian regression model is established. On the basis of the existing port throughput prediction theory and actual situation of ports in China, through the analysis of China's coastal port cargo and impact, a coastal port cluster cargo throughput prediction model, improve China's coastal port throughput prediction precision and accuracy, which provides more reliable reference for China's coastal areas port investment planning. The main features of this model are as follows. For the first time, we analyze and predict the throughput of coastal ports from the point of view of the composition of port throughput. Considering the coordination relationship between major coastal port cargo throughput under, we use game theory, to deal with the port cargo throughput index, the maximum information is retained to ensure the accuracy of prediction model. The model is convenient and flexible, and can be extended to the throughput prediction of a single port or port group. It can be extended to the prediction problem with more time series indexes under multimedia environment.