Abstract
© 2022 Elsevier B.V.First and last mile connectivity are the most crucial elements of transit system. However, inadequate attention is given to such issues in developing countries like India. The present study aims to analyze feeder mode choice behavior of people accessing Delhi metro. Multinomial logit model and Artificial Neural Network are deployed to analyze the travel behavior. Findings suggest that ANNs are highly efficient in learning and recognizing connections between parameters for best prediction of an outcome. Since, utility of ANNs has been critically limited due to its ‘Black Box’ nature, the study involves the use of Garson's algorithm and Partial Dependence Plots for model interpretation. Findings of the study can be useful for policy makers and transport planners for improving service quality of existing feeder services and, establishing efficient feeder system that promote the use of transit.
NSTL