Charisma F. Choudhury

arXiv2025

Beyond utility: incorporating eye-tracking, skin conductance and heart rate data into cognitive and econometric travel behaviour models

Choice models for large-scale applications have historically relied on economic theories (e.g. utility maximisation) that establish relationships between the choices of individuals, their characteristics, and the attributes of the alternatives. In a parallel stream, choice models in cognitive psychology have focused on modelling the decision-making process, but typically in controlled scenarios. Recent research developments have attempted to bridge the modelling paradigms, with choice models that are based on psychological foundations, such as decision field theory (DFT), outperforming traditional econometric choice models for travel mode and route choice behaviour. The use of physiological data, which can provide indications about the choice-making process and mental states, opens up the opportunity to further advance the models. In particular, the use of such data to enrich 'process' parameters within a cognitive theory-driven choice model has not yet been explored. This research gap is addressed by incorporating physiological data into both econometric and DFT models for understanding decision-making in two different contexts: stated-preference responses (static) of accomodation choice and gap-acceptance decisions within a driving simulator experiment (dynamic). Results from models for the static scenarios demonstrate that both models can improve substantially through the incorporation of eye-tracking information. Results from models for the dynamic scenarios suggest that stress measurement and eye-tracking data can be linked with process parameters in DFT, resulting in larger improvements in comparison to simpler methods for incorporating this data in either DFT or econometric models. The findings provide insights into the value added by physiological data as well as the performance of different candidate modelling frameworks for integrating such data.

econ.EM↗

arXiv2023

Determining Causality in Travel Mode Choice

This article presents one of the pioneering studies on causal modeling in travel mode choice decision-making using causal discovery algorithms. These models are a major advancement from conventional correlation-based techniques. We propose a novel methodology that combines causal discovery with structural equation modeling (SEM). This modeling approach overcomes some of the limitations of SEM by combining the strengths of both causal discovery and SEM. Causal discovery algorithms determine causal graphs from observational data and domain knowledge, and SEMs estimate direct causal effects and test the performance of causal discovery algorithms. In this study, we test four causal discovery algorithms: Peter-Clark (PC), Fast Causal Inference (FCI), Fast Greedy Equivalence Search (FGES), and Direct Linear Non-Gaussian Acyclic Models (DirectLiNGAM). The results show that DirectLiNGAM based SEM model best captures causality in mode choice behavior. It passes several goodness-of-fit tests, including Root Mean Square Error of Approximation (RMSEA) and Goodness-of-Fit Index (GFI), and it achieves the lowest Bayesian Information Criterion (BIC) value. The analyses are conducted on data collected from the 2017 National Household Travel Survey in the New York Metropolitan area.

stat.AP↗