Using artificial neural networks to predict container flows between the major ports of Asia

Feng-Ming Tsai and Linda J.W. Huang

International Journal of Production Research, 2017, vol. 55, issue 17, 5001-5010

Abstract: Container flow information is a critical issue for port operators and liners to support their strategic planning and decision-making. This study uses artificial neural networks (ANNs) to predict container flows by considering GDP, interest rates, the value of export and import trade, the numbers of export and import containers and the number of quay cranes. ANNs are developed for data mining purposes, and the developed model can simultaneously predict container flows between the major ports of Asia. The forecasting results indicate that the prediction errors are relatively small in most selected ports, and thus shipping companies can use the container flow prediction model to make decisions concerning operations. The results can be further applied to the trend analysis of container flows among the major ports of Asia, and a community analysis of the containers was conducted for the purpose of supply chain management.

Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://hdl.handle.net/10.1080/00207543.2015.1112046 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tprsxx:v:55:y:2017:i:17:p:5001-5010

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TPRS20

DOI: 10.1080/00207543.2015.1112046

Access Statistics for this article

International Journal of Production Research is currently edited by Professor A. Dolgui

More articles in International Journal of Production Research from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().