Forecasting container throughputs at ports using genetic programming

doi:10.1016/j.eswa.2009.06.054

Forecasting container throughputs at ports using genetic programming

2010-03-15

95

PRE

AI

DOI：10.1016/j.eswa.2009.06.054

Original

Original request for help

Save

Abstract

En 中文

To accurately forecast container throughput is crucial to the success of any port operation policy. This study attempts to create an optimal predictive model of volumes of container throughput at ports by using genetic programming (GP), decomposition approach (X-11), and seasonal auto regression integrated moving average (SARIMA). Twenty-nine years of historical data from Taiwan's major ports were collected to establish and validate a forecasting model. The Mean Absolute Percent Error levels between forecast and actual data were within 4% for all three approaches. The GP model predictions were about 32-36% better than those of X-11 and SARIMA. These results suggest that GP is the optimal method for this case. GP predicted that container throughputs at Taiwan's major ports would slowly increase in the year 2008. Since Taiwan's government opened direct transportation with China in July 2008, the issue of container throughput in Taiwan has become even more worthy of discussion. Crown Copyright (C) 2009 Published by Elsevier Ltd. All rights reserved.

Keywords:

Container throughput

Forecasting

Genetic programming

Forecasting container throughputs at ports using genetic programming

Abstract

AI Summary

Journal

Organization

Cited Papers