On-Demand Technologies for Public Transport: Insights From a Melbourne Survey

Abstract

The integration of on-demand technologies in urban mobility requires a comprehensive understanding of user acceptance and willingness to pay for innovative modes like on-demand public transport designed to enhance conventional services. This study presents findings from a survey conducted in Melbourne, highlighting passenger behaviours, preferences, and attitudes towards the use of on-demand transport technologies as a sustainable alternative to conventional bus services. Data from 510 diverse participants revealed a strong preference for private vehicles, mainly for convenience and flexibility. However, concerns regarding waiting times, crowding, and reliability in public transport highlighted the need for service improvements. The survey included hypothetical scenarios where respondents evaluated on-demand transport options with varying factors like waiting time, travel cost, and journey duration. Using binary logistic regression and neural networks (NN), the study analysed preferences for the proposed hypothetical on-demand transport scenarios, revealing that while travel cost negatively impacts mode choice, reduced waiting times positively influence it. The binary logistic model showed classification accuracies between 64% and 72%, while the NN models achieved a high prediction accuracy, reaching approximately 91%. The results indicate that 67% would switch to on-demand transport if it offered reliability, convenience, reduced crowding, and fair pricing. Additionally, 53% were willing to pay a 25% premium for shorter walking and waiting times, with 69% identifying service reliability as the key factor influencing their transport decisions. These insights are essential for developing transport technology frameworks that incorporate on-demand technologies within existing public transport systems, thus advancing sustainable and resilient urban mobility solutions.