A comparative study of machine learning, deep neural networks and random utility maximization models for travel mode choice modelling
24th Euro Working Group on Transportation Meeting (EWGT 2021)
José Ángel Martín Baos
Abstract
Traditionally, Random Utility Maximization (RUM) models have been widely applied to travel mode choice modelling. Currently, Machine Learning (ML) models are being applied as an alternative to RUM models, since they provide better results in terms of prediction capability and they can manage large volumes of data. In this paper, a comprehensive comparison between classic RUM models and ML models, including single and ensemble classifiers as well as Deep Neural Networks (DNNs), is provided in order to assess systematically the performance of different models over two different datasets which have different sizes and nature of data. Numerical experiments show Random Forest (RF) is the best classifier in terms of accuracy index and the computational cost to train the model.
José Ángel Martín Baos is an Assistant Professor (PhD) at the Escuela Superior de Informática of the University of Castilla-La Mancha. He obtained his PhD in Advanced Computer Technologies from the University of Castilla-La Mancha in 2023. There, he graduated with honors on both a BSc. in computer science in the year 2018, and a MSc. in computer science in the year 2019.
Since 2016, José Ángel has been working as a researcher in the MAT (Modelos y Algoritmos en Sistemas de Transportes) research group at the University of Castilla-La Mancha. His research focuses on the use of machine learning models and artificial intelligence for solving optimization problems in the field of transportation. Specifically, he has worked on the application of machine learning models for transport demand modeling.