MétaCan
Menu
Back to cohort
Record W4416887687 · doi:10.1016/j.trip.2025.101754

Understanding travel behavior and mode choice prediction for university commuters: insights from discrete choice models and machine learning

2025· article· en· W4416887687 on OpenAlexafffundabout
Hassan Kamkar, Saeid Saidi, Mohammad Ansari Esfeh

Bibliographic record

VenueTransportation Research Interdisciplinary Perspectives · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicUrban Transport and Accessibility
Canadian institutionsUniversity of Calgary
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsMode choiceMultinomial logistic regressionDiscrete choiceMode (computer interface)Travel behaviorChoice setChoice modellingPublic transportMixed logit

Abstract

fetched live from OpenAlex

• University commuters’ mode choice is analyzed using DCMs & ML techniques. • Effect of built-environment, socioeconomic, and travel info factors is explored. • The two models prioritize data differently: MNL on demographics, ML on travel data. • MNL and ML models complement each other, enhancing insights from data analysis. • Car ownership, household size, and income significantly affect transit and walk choice. While there has been a growing interest in studying the commuting behavior of university students using mode choice models, most existing studies still lack the in-depth analysis needed to fully understand the factors influencing their transportation mode choices. To address this gap, this study examines the effects of various built-environment factors, socio-economic factors, and travel information to explore the commuting behavior of university commuters. Various prediction models based on discrete choice models (DCMs) and machine learning (ML) techniques are developed to predict the travel mode choice of university commuters. The developed prediction models are tested using a Commuting Habits survey conducted at a Canadian university. The results indicate that for transit and walk, household attributes such as car ownership, household size, and income level have significant impacts on choosing these modes as primary modes of transportation. It was also observed that car ownership and availability of transit passes are the most influential factors. As such, policymakers can further examine these relationships to incentivize commuters to promote sustainable transportation modes. Comparing DCM and ML-based models to predict the mode choice of university commuters, our analysis revealed that although the multinomial logit discrete choice (MNL) model resulted in lower performance in predicting commuters’ travel mode choices, it provides more insightful information regarding each specific mode of transportation. ML models prioritize information differently when making predictions, with MNL placing more emphasis on socio-demographic variables and household characteristics of respondents, whereas ML algorithms rely more on revealed travel-related variables.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.038
Threshold uncertainty score0.076

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.012
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.158
GPT teacher head0.417
Teacher spread0.260 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes3
Has abstractyes

Explore more

Same venueTransportation Research Interdisciplinary PerspectivesSame topicUrban Transport and AccessibilityFrench-language works237,207