Transaction-Driven Mobility Analysis for Travel Mode Choices

Jesper Slik; Sandjai Bhulai

doi:10.1016/j.procs.2020.03.022

Transaction-Driven Mobility Analysis for Travel Mode Choices

Jesper Slik^*, Sandjai Bhulai

^*Corresponding author for this work

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

Urban planning can benefit tremendously from a better understanding of where, when, why, how people travel. Through advances in technology, detailed data on the travel behavior of individuals has become available. This data can be leveraged to understand why one prefers one mode of transportation over another one. In this paper, we analyze a unique dataset through which we can address this question. We show that the travel behavior in our dataset is highly predictable, with an accuracy of 97%. The main predictors are reachability features, more so than specific travel times. Moreover, the travel type (commute or personal) has a considerable influence on travel mode choice.

Original language	English
Pages (from-to)	169-176
Number of pages	8
Journal	Procedia Computer Science
Volume	170
Early online date	14 Apr 2020
DOIs	https://doi.org/10.1016/j.procs.2020.03.022
Publication status	Published - 2020
Event	11th International Conference on Ambient Systems, Networks and Technologies, ANT 2020 / 3rd International Conference on Emerging Data and Industry 4.0, EDI40 2020 / Affiliated Workshops - Warsaw, Poland Duration: 6 Apr 2020 → 9 Apr 2020

Keywords

logit model
machine learning
mobility analysis
travel mode choices
trip data

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.procs.2020.03.022

Persistent URL (handle)

Persistent link

Cite this

@article{291b4c1f76b743db8c6c5ddd224471c5,

title = "Transaction-Driven Mobility Analysis for Travel Mode Choices",

abstract = "Urban planning can benefit tremendously from a better understanding of where, when, why, how people travel. Through advances in technology, detailed data on the travel behavior of individuals has become available. This data can be leveraged to understand why one prefers one mode of transportation over another one. In this paper, we analyze a unique dataset through which we can address this question. We show that the travel behavior in our dataset is highly predictable, with an accuracy of 97%. The main predictors are reachability features, more so than specific travel times. Moreover, the travel type (commute or personal) has a considerable influence on travel mode choice.",

keywords = "logit model, machine learning, mobility analysis, travel mode choices, trip data",

author = "Jesper Slik and Sandjai Bhulai",

year = "2020",

doi = "10.1016/j.procs.2020.03.022",

language = "English",

volume = "170",

pages = "169--176",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier BV",

note = "11th International Conference on Ambient Systems, Networks and Technologies, ANT 2020 / 3rd International Conference on Emerging Data and Industry 4.0, EDI40 2020 / Affiliated Workshops ; Conference date: 06-04-2020 Through 09-04-2020",

}

TY - JOUR

T1 - Transaction-Driven Mobility Analysis for Travel Mode Choices

AU - Slik, Jesper

AU - Bhulai, Sandjai

PY - 2020

Y1 - 2020

N2 - Urban planning can benefit tremendously from a better understanding of where, when, why, how people travel. Through advances in technology, detailed data on the travel behavior of individuals has become available. This data can be leveraged to understand why one prefers one mode of transportation over another one. In this paper, we analyze a unique dataset through which we can address this question. We show that the travel behavior in our dataset is highly predictable, with an accuracy of 97%. The main predictors are reachability features, more so than specific travel times. Moreover, the travel type (commute or personal) has a considerable influence on travel mode choice.

AB - Urban planning can benefit tremendously from a better understanding of where, when, why, how people travel. Through advances in technology, detailed data on the travel behavior of individuals has become available. This data can be leveraged to understand why one prefers one mode of transportation over another one. In this paper, we analyze a unique dataset through which we can address this question. We show that the travel behavior in our dataset is highly predictable, with an accuracy of 97%. The main predictors are reachability features, more so than specific travel times. Moreover, the travel type (commute or personal) has a considerable influence on travel mode choice.

KW - logit model

KW - machine learning

KW - mobility analysis

KW - travel mode choices

KW - trip data

UR - http://www.scopus.com/inward/record.url?scp=85085579794&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085579794&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2020.03.022

DO - 10.1016/j.procs.2020.03.022

M3 - Article

AN - SCOPUS:85085579794

SN - 1877-0509

VL - 170

SP - 169

EP - 176

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 11th International Conference on Ambient Systems, Networks and Technologies, ANT 2020 / 3rd International Conference on Emerging Data and Industry 4.0, EDI40 2020 / Affiliated Workshops

Y2 - 6 April 2020 through 9 April 2020

ER -

Transaction-Driven Mobility Analysis for Travel Mode Choices

Abstract

Keywords

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this