Dynamic pricing research for container terminal handling charge

The purpose of this study is to provide a new pricing strategy for the container terminal handling charge (THC) of terminals. A dynamic pricing model is established by using the Back Propagation Neural Network (BPNN) algorithm and the Time-Driven Activity-Based Costing method. This pricing strategy can dynamically amend the price of the container THC based on handling demand, recent charge standards per container, and handling time for a particular customer. To some extent, this dynamic pricing strategy can provide a valuable reference for terminals in pricing decisions. This case study implemented the dynamic pricing model at the Shanghai ShengDong International Container Terminal, one of the largest container terminals in China. The results show that this pricing model dynamically adjusts the container THC depending on customers' handling conditions. Besides, this dynamic pricing model is more precise than the traditional contractual pricing used at the terminal. Compared with the BPNN algorithm, the optimized BPNN algorithm has faster convergence speed and less learning error. Moreover, this pricing method is universally applicable to the container THC pricing problem of most terminals.