Forecasting Port Throughput Model of Tianjin Port based on Wavelet Analysis and Machine Learning

DOI

10.2991/ssmi-18.2019.50How to use a DOI?

Keywords

Tianjin port, cargo throughput, machine learning, forecasting, wavelet analysis.

Abstract

With the development of national economy, the importance of port growing port is the national foreign trade portal, is the driving force for the development of the city, with the improvement of freight volume, how many directly affects the port cargo throughput of port layout planning, therefore, to effectively predict the Tianjin port cargo throughput is very important to the correct port development policy. This article embarks from the analysis of Tianjin port cargo throughput changes year by year, from 2001 to 2017, Tianjin port cargo throughput are summarized factors index, prediction model was established based on seven kinds of machine learning algorithms and wavelet analysis, in Tianjin, for example, through the training data model, and then the model prediction data were compared with the actual data analysis, weighing error, select the optimal model, it is concluded that the prediction data and the actual data, the basic of Tianjin port cargo throughput forecast has positive significance.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bingchun Liu
AU  - Shaofeng Feng
PY  - 2019/02
DA  - 2019/02
TI  - Forecasting Port Throughput Model of Tianjin Port based on Wavelet Analysis and Machine Learning
BT  - Proceedings of the 2018 International Symposium on Social Science and Management Innovation (SSMI 2018)
PB  - Atlantis Press
SP  - 282
EP  - 285
SN  - 2352-5428
UR  - https://doi.org/10.2991/ssmi-18.2019.50
DO  - 10.2991/ssmi-18.2019.50
ID  - Liu2019/02
ER  -