Cluster analysis with Gaussian mixture models for Mobility as a Service (MaaS) users with a case study from the Solent area

The Solent Future Transport Zone programme, funded by the Department for Transport, has developed a novel multi-city Mobility as a Service (MaaS) app, Breeze, to shift travel behaviour towards sustainable modes in the car-dependent Solent area. MaaS has been implemented globally over the past decade due to its potential for enabling shifts towards more sustainable travel modes. Despite numerous trials and implementations, existing studies mostly focus on the potential adoption and uptake of MaaS rather than the profile analysis of MaaS users. Understanding socio-demographics, travel behaviour, and intentions to engage with MaaS is important to evaluate the reach of MaaS and create strategies to enhance uptake among less-engaged populations. This study proposes a Gaussian Mixture Model (GMM) analysis method to define the Breeze user segments. Data from 1642 Breeze app users, collected through revealed preference surveys, were analysed using GMM on Python. We identified six clusters primarily based on the mode share of participants. The resulting clusters provide insights that can help develop strategies to enhance the reach of the Beeze app and guide targeted marketing to increase engagement among current users. It will also identify the limitations of MaaS’s reach in developing future MaaS applications in car-dependent regions.