search for




 

A machine learning approach to the prediction of individual travel mode choices
Journal of the Korean Data & Information Science Society 2019;30:1011-24
Published online September 30, 2019;  https://doi.org/10.7465/jkdi.2019.30.5.1011
© 2019 Korean Data and Information Science Society.

Youngho Lee1 · Seong-Yun Hong2

12Department of Geograpy, Kyung Hee University
Correspondence to: Assistant professor, Department of Geography, Kyung Hee University, Seoul 02447, Korea. E-mail: syhong@khu.ac.kr
Received April 20, 2019; Revised June 7, 2019; Accepted July 18, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
A reliable prediction of individual travel mode choices is an important factor for implementing transportation polices, because it is directly related to the demand for transport services and infrastructure. While machine learning methods have become increasingly popular in this field, it is not widely applied in the Korea context. In this paper, we attempt to develop a model that can predict individual travel mode choices by comparing three different machine learning techniques, multinomial logistic regression, decision tree and support vector machine. The performance of the prediction models is evaluated using a confusion matrix, and the results show that the model developed by support vector machine performs better than other methods. Our analysis can contribute to the expansion of transportation policies and support management decision-making.
Keywords : Machine learning, prediction model, support vector machine, travel mode.