The seaport service rate prediction system: Using drayage truck trajectory data to predict seaport service rates

Highlights：

• This study presents a seaport service rate prediction system that will help drayage operators to predict the duration of the pick-up/delivery operation at a seaport by using their subordinate trucks’ trajectory data.

• With the proposed approach, the seaport service rate can be estimated without modifying the existing design of the seaports appointment system.

• The seaport service rate prediction system is constructed based on three components namely, trajectory reconstruction, geo-fencing analysis, and gradient boosting modelling.

• Using predictive analytic techniques, the prediction system is trained and validated using more than 15 million data records from over 200 trucks over a period of 19 months.

摘要

For drayage operators the service rate of seaports is crucial for organizing their container pick-up/delivery operations. This study presents a seaport service rate prediction system that could help drayage operators to improve their predictions of the duration of the pick-up/delivery operations at a seaport by using the subordinate trucks' trajectory data. The system is constructed based on three components namely, trajectory reconstruction, geo-fencing analysis, and gradient boosting modelling. Using predictive analytic techniques, the prediction system is trained and validated using more than 15 million data records from over 200 trucks over a period of 19 months. The gradient boosting model-based solution provides better predictions compared with the linear model benchmark solution. Conclusions and implications are formulated.

论文关键词：Predictive analytics,Gradient boosting model,Trajectory data,Vehicle telematics system,Seaport appointment system,Drayage operation

论文评审过程：Received 23 August 2015, Revised 10 October 2016, Accepted 29 November 2016, Available online 1 December 2016, Version of Record 3 March 2017.