How to identify factors influencing mode choice behaviors within a heterogeneous metropolitan area? A novel approach midway between data science and econometrics

Rémy Le Boennec (), Fouad Hadj Selem, Ghazaleh Khodabandelou () and Jaâfar Berrada ()
Additional contact information
Rémy Le Boennec: MATRiS - Mobilité, Aménagement, Transports, Risques et Société - Cerema - Centre d'Etudes et d'Expertise sur les Risques, l'Environnement, la Mobilité et l'Aménagement - CY - CY Cergy Paris Université
Fouad Hadj Selem: ENTROPY
Ghazaleh Khodabandelou: LISSI - Laboratoire Images, Signaux et Systèmes Intelligents - UPEC UP12 - Université Paris-Est Créteil Val-de-Marne - Paris 12
Jaâfar Berrada: VeDeCom - VEhicule DEcarboné et COmmuniquant et sa Mobilité

Post-Print from HAL

Abstract: Estimating factors influencing mode choice behaviors has posed a significant challenge for decision makers. In this paper, we propose a three-step method to estimate mode choice between public transportation and private vehicles within a heterogeneous metropolitan area. First, we implement a deep learning model, Altaïr, capable of inferring travel times and travel flows by leveraging multi-source input data (Step 1). To identify homogeneous sub-regions regarding mode choice behaviors, two data clustering models are performed: k-means and a Gaussian Mixture Model (GMM, Step 2). The GMM reveals three spatial clusters based on the relationships between relative travel times and relative travel flows in public transportation and private vehicles. Moreover, an econometric model (robust ordinary least squares) is employed to identify additional explanatory variables, including sociodemographic features and location variables (Step 3). This hybrid method is currently employed in the Paris metropolitan area (France). At the metropolitan level, we find that competitive travel times in public transportation lead to higher ridership. Conversely, when the time ratio exceeds approximately 3.5–4, public transportation use becomes negligible in comparison to private vehicles. This hybrid method allows for precise, interpretable prediction of mode choice between public transportation and private vehicles. The method's results are close to those of the regional Household Travel Surveys (HTS), as shown in a validation analysis. The design ensures the transferability of the method to any metropolitan area, including areas with incomplete data.

Keywords: Econometric model; Data clustering model; Deep learning model; Travel flow; Mode choice behavior (search for similar items in EconPapers)
Date: 2025-06-26
References: Add references at CitEc
Citations:

Published in European Transport Congress 2025, Jun 2025, Cergy (CY Cergy Paris université), France

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05250045

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().