Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning

Xiaolu Zhou, Mingshu Wang, Dongying Li

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

In many big cities, the bike-sharing system (BSS) and taxi play critical roles in transportation services. They both offer on-demand transportation options and allow flexible riding scheduling and routing. Previous literature has compared BSS and taxi to other transport modes, such as public transit and private automobile, but little is known about the spatiotemporal factors that influence travel choices between these two alternatives. Understanding travel patterns of BSS and taxi is critical in traffic demand analysis and sustainable transportation planning. Also, an in-depth examination of the patterns of travel behaviors, especially when one would choose BSS over a taxi, will provide valuable insights on human mobility and active living research. In this study, we investigated the spatiotemporal patterns of BSS and taxi trips in Chicago from 2014 to 2016. To model travel choices between BSS and taxi, we applied machine learning techniques to simulate the means of transport based on environmental and temporal factors. Results show seasonal trip variations of the BSS and a declining trend of taxi trips. BSS speed is relatively stable while taxi speed varies primarily because of time and locations. Based on the random forest model, which has demonstrated the best fit with high processing speed, travel distance and the number of parks and recreational facilities seem to be critical spatial predicting factors of the travel choice. Given any time and location, the model can recommend the travel choices between BSS and taxis for users. This study shows the significance of machine learning techniques in urban mobility research. Results of the study may potentially support people's transportation decision-making and facilitate sustainable transportation planning.
Original languageEnglish
Article number102479
JournalJournal of transport geography
Volume79
DOIs
Publication statusPublished - 30 Jul 2019

Fingerprint

taxis
Learning systems
travel
learning
modeling
Recreational facilities
transportation planning
Planning
Automobiles
mobility research
recreational facilities
recreational facility
demand analysis
means of transport
Decision making
Scheduling
machine learning
seasonal variation
travel behavior
planning

Keywords

  • ITC-ISI-JOURNAL-ARTICLE

Cite this

@article{f397039ecc074e38804bf361f0feef33,
title = "Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning",
abstract = "In many big cities, the bike-sharing system (BSS) and taxi play critical roles in transportation services. They both offer on-demand transportation options and allow flexible riding scheduling and routing. Previous literature has compared BSS and taxi to other transport modes, such as public transit and private automobile, but little is known about the spatiotemporal factors that influence travel choices between these two alternatives. Understanding travel patterns of BSS and taxi is critical in traffic demand analysis and sustainable transportation planning. Also, an in-depth examination of the patterns of travel behaviors, especially when one would choose BSS over a taxi, will provide valuable insights on human mobility and active living research. In this study, we investigated the spatiotemporal patterns of BSS and taxi trips in Chicago from 2014 to 2016. To model travel choices between BSS and taxi, we applied machine learning techniques to simulate the means of transport based on environmental and temporal factors. Results show seasonal trip variations of the BSS and a declining trend of taxi trips. BSS speed is relatively stable while taxi speed varies primarily because of time and locations. Based on the random forest model, which has demonstrated the best fit with high processing speed, travel distance and the number of parks and recreational facilities seem to be critical spatial predicting factors of the travel choice. Given any time and location, the model can recommend the travel choices between BSS and taxis for users. This study shows the significance of machine learning techniques in urban mobility research. Results of the study may potentially support people's transportation decision-making and facilitate sustainable transportation planning.",
keywords = "ITC-ISI-JOURNAL-ARTICLE",
author = "Xiaolu Zhou and Mingshu Wang and Dongying Li",
year = "2019",
month = "7",
day = "30",
doi = "10.1016/j.jtrangeo.2019.102479",
language = "English",
volume = "79",
journal = "Journal of transport geography",
issn = "0966-6923",
publisher = "Elsevier",

}

Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning. / Zhou, Xiaolu; Wang, Mingshu ; Li, Dongying.

In: Journal of transport geography, Vol. 79, 102479, 30.07.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Bike-sharing or taxi? Modeling the choices of travel mode in Chicago using machine learning

AU - Zhou, Xiaolu

AU - Wang, Mingshu

AU - Li, Dongying

PY - 2019/7/30

Y1 - 2019/7/30

N2 - In many big cities, the bike-sharing system (BSS) and taxi play critical roles in transportation services. They both offer on-demand transportation options and allow flexible riding scheduling and routing. Previous literature has compared BSS and taxi to other transport modes, such as public transit and private automobile, but little is known about the spatiotemporal factors that influence travel choices between these two alternatives. Understanding travel patterns of BSS and taxi is critical in traffic demand analysis and sustainable transportation planning. Also, an in-depth examination of the patterns of travel behaviors, especially when one would choose BSS over a taxi, will provide valuable insights on human mobility and active living research. In this study, we investigated the spatiotemporal patterns of BSS and taxi trips in Chicago from 2014 to 2016. To model travel choices between BSS and taxi, we applied machine learning techniques to simulate the means of transport based on environmental and temporal factors. Results show seasonal trip variations of the BSS and a declining trend of taxi trips. BSS speed is relatively stable while taxi speed varies primarily because of time and locations. Based on the random forest model, which has demonstrated the best fit with high processing speed, travel distance and the number of parks and recreational facilities seem to be critical spatial predicting factors of the travel choice. Given any time and location, the model can recommend the travel choices between BSS and taxis for users. This study shows the significance of machine learning techniques in urban mobility research. Results of the study may potentially support people's transportation decision-making and facilitate sustainable transportation planning.

AB - In many big cities, the bike-sharing system (BSS) and taxi play critical roles in transportation services. They both offer on-demand transportation options and allow flexible riding scheduling and routing. Previous literature has compared BSS and taxi to other transport modes, such as public transit and private automobile, but little is known about the spatiotemporal factors that influence travel choices between these two alternatives. Understanding travel patterns of BSS and taxi is critical in traffic demand analysis and sustainable transportation planning. Also, an in-depth examination of the patterns of travel behaviors, especially when one would choose BSS over a taxi, will provide valuable insights on human mobility and active living research. In this study, we investigated the spatiotemporal patterns of BSS and taxi trips in Chicago from 2014 to 2016. To model travel choices between BSS and taxi, we applied machine learning techniques to simulate the means of transport based on environmental and temporal factors. Results show seasonal trip variations of the BSS and a declining trend of taxi trips. BSS speed is relatively stable while taxi speed varies primarily because of time and locations. Based on the random forest model, which has demonstrated the best fit with high processing speed, travel distance and the number of parks and recreational facilities seem to be critical spatial predicting factors of the travel choice. Given any time and location, the model can recommend the travel choices between BSS and taxis for users. This study shows the significance of machine learning techniques in urban mobility research. Results of the study may potentially support people's transportation decision-making and facilitate sustainable transportation planning.

KW - ITC-ISI-JOURNAL-ARTICLE

UR - https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2019/isi/mingshuwang_bik.pdf

U2 - 10.1016/j.jtrangeo.2019.102479

DO - 10.1016/j.jtrangeo.2019.102479

M3 - Article

VL - 79

JO - Journal of transport geography

JF - Journal of transport geography

SN - 0966-6923

M1 - 102479

ER -