A Model to Estimate Container Dwell Time Using a Set of Determinants

Numerous options are being considered in practice, and several have been captured in theoretical research, for increasing container terminal capacity in seaports. These include acquiring new equipment, optimizing yard space allocation, and creating empty container depots outside of terminals, to mention a few. Among these, reducing the amount of time a container spends at the terminal, container dwell time (CDT), may prove to be one of the least costly solutions. For this strategy to be successful, it is essential that terminal operators be able to define factors impacting the CDT and accurately estimate how long a container will remain in the yard. This paper attempts to identify determinants of CDT and delineate appropriate computational tools for estimating CDT based on a set of determinants on which terminal operators typically collect data. The paper compares the performance of three data mining algorithms for estimating CDT: Naive Bayes (NB), decision tree, and a NB-decision tree hybrid (NBtree). Using the best performing model, sample terminal data is used to measure how changes in CDT determinants impact CDT, yard capacity, and terminal revenue. This research potentially provides members of the port, trade, and transportation community with a useful tool for establishing appropriate policies to improve container terminal capacity and revenue

Language

  • English

Media Info

  • Media Type: DVD
  • Features: References; Tables;
  • Pagination: 19p
  • Monograph Title: TRB 89th Annual Meeting Compendium of Papers DVD

Subject/Index Terms

Filing Info

  • Accession Number: 01154365
  • Record Type: Publication
  • Report/Paper Numbers: 10-3583
  • Files: TRIS, TRB
  • Created Date: Apr 14 2010 7:14AM