Multinomial Logit Model for Transportation Mode Choice: A Comprehensive Python Implementation with Scikit-Learn and Stats Models

International Journal of Civil Engineering

© 2024 by SSRG - IJCE Journal

Volume 11 Issue 7

Year of Publication : 2024

Authors : Priya Hirave, Vidula Sohoni

10.14445/23488352/IJCE-V11I7P102

How to Cite?

Priya Hirave, Vidula Sohoni, "Multinomial Logit Model for Transportation Mode Choice: A Comprehensive Python Implementation with Scikit-Learn and Stats Models," SSRG International Journal of Civil Engineering, vol. 11,  no. 7, pp. 20-27, 2024. Crossref, https://doi.org/10.14445/23488352/IJCE-V11I7P102

Abstract:

This paper examines the dynamics of transportation mode choices in response to evolving urban landscapes, utilizing the Multinomial Logit (MNL) model with the Python programming language. The aim is to provide valuable insights for researchers and practitioners across diverse contexts. As cities undergo continual transformations, understanding the connection between these changes and transportation choices becomes crucial. The adaptable Multinomial Logit model, implemented through Python, enhances the study's versatility and applicability. To fortify the research, two significant tools are strategically employed: scikit-learn for machine learning capabilities and stats models for comprehensive statistical analysis. The combined use of these tools seeks to unravel the nuanced dynamics of transportation mode choices. The paper meticulously details the methodology, offering a transparent exploration of the intricate relationships between urban evolution and transportation decisions.

Keywords:

Evolving urban landscapes, Transportation choices, Multinomial logit model, Python programming, Scikit-learn, Stats models, Machine learning, Statistical analysis, City transformations, Modeling techniques, Valuable insights.

References:

[1] Kaveh Shafiee et al., “Modeling and Simulation of Vehicular Networks,” DIVANet '11: Proceedings of the First ACM International Symposium on Design and Analysis of Intelligent Vehicular Networks and Applications, Miami Florida USA, pp. 77-86, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Maja M. Popović, and Jadranka J. Jović, “Concept of Expert System for Modal Split in Transportation Planning,” Yugoslav Journal of Operations Research, vol. 16, no. 1, pp. 107-124, 2006.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Li Jie et al., “Calibration of a Micro Simulation Program for a Chinese City,” Procedia - Social and Behavioral Sciences, vol. 20, pp. 263- 272, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Michael P. Hunter et al., “An Investigation of Real-Time Dynamic Data Driven Transportation Simulation,” Proceedings of the 2006 Winter Simulation Conference, Monterey, CA, USA, pp. 1414-1421, 2006.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Muhammad Moazzam Ishaque, and Robert B. Noland, “Pedestrian and Vehicle Flow Calibration in Multimodal Traffic Microsimulation,” Journal of Transportation Engineering, vol. 135, no. 6, pp. 338-348, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Li-Jun Tiana, and Hai-Jun Huang, “Modeling the Modal Split and Trip Scheduling with Commuters’ Uncertainty Expectation,” European Journal of Operational Research, vol. 244, no. 3, pp. 815-822, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Gordana Štefančić, Ninoslav Nogić, and Drago Bago, “Models in Planning Urban Public Passenger Transport,” Promet-Traffic&Transportation, vol. 19, no. 4, pp. 259-262, 2007.
[Google Scholar] [Publisher Link]
[8] “Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specification,” IEEE Std, vol. 12, no. 11, pp. 260-280, 1997.
[Google Scholar]