Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

TL;DR

This paper introduces a generative machine learning framework using Restricted Boltzmann Machines to identify latent travel behavior traits, outperforming traditional models in complex decision-making analysis.

Contribution

It presents a novel Bayesian graphical network model with RBMs for travel behavior analysis, demonstrating improved performance over traditional latent variable models.

Findings

RBM-based model improves likelihood statistics

Identifies meaningful latent variables related to safety, comfort, and environment

Machine learning effectively models complex travel behavior interactions

Abstract

In this paper, we implement an information-theoretic approach to travel behaviour analysis by introducing a generative modelling framework to identify informative latent characteristics in travel decision making. It involves developing a joint tri-partite Bayesian graphical network model using a Restricted Boltzmann Machine (RBM) generative modelling framework. We apply this framework on a mode choice survey data to identify abstract latent variables and compare the performance with a traditional latent variable model with specific latent preferences -- safety, comfort, and environmental. Data collected from a joint stated and revealed preference mode choice survey in Quebec, Canada were used to calibrate the RBM model. Results show that a signficant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.