A statistical forecasting model applied to container throughput in a multi-port gateway system: the Barcelona-Tarragona-Valencia case
Rights accessRestricted access - publisher's policy (embargoed until 2020-05-03)
This contribution investigates the container throughput flow in a multi-port gateway system: Barcelona-Tarragona-Valencia (BTV). First, the paper examine the recent dynamics of the total and transshipment flow showing a relevant shifting of traffic share from Barcelona to Valencia. A statistical model based on a two-state Markov model in conjunction with a Monte Carlo experiments is implemented to estimate the predictions of container throughput in BTV system. Verification tests shows how the predictions are reasonable good with an error metrics similar to other methods based on time series analysis. The method is considered suitable for short-term forecasting with a strong potential to be used as a complement of qualitative methods due to the statistical nature of the results. The implementation of the method considers separately the import/export and transhipment container throughput revealing a differentiate dynamics in both container flows. The transhipment flow is more volatile and induce more data dispersion in the container throughput predictions.
CitationGrifoll, M. A statistical forecasting model applied to container throughput in a multi-port gateway system: the Barcelona-Tarragona-Valencia case. "International journal of shipping and transport logistics", Abril 2019, vol. 11, núm. 4, p. 316-333.