Disaggregate travel demand analysis using big data sources: unsupervised learning methods for data-driven trip purpose estimation

Data is a paramount factor in the success of transport modeling. Smartphones can be employed to retrieve full individual trajectories, either locally through apps using the devices’ integrated GPS sensors, or through the mobile network operator (MNO), by tracing the mobile antennas to which devices connect over time. Several studies have demonstrated of the utility of this data to infer users’ door-to-door trips, and then to build door-to-door origin-destination matrices, which are a key feedstock for transport modeling and planning. Some MNOs already provide such services commercially, yielding notable time and cost savings with respect to matrices estimated through traditional surveys. However, these are often highly aggregated and lack supplementary relevant trip information, such as mode and purpose, and if any, these are commonly obtained by means of human-driven heuristic considerations and fixed rules. This study aims at exploring the suitability of machine learning techniques for data-driven mobility demand estimation and analysis. It identifies associated opportunities and challenges through a pilot experiment focused on trip purpose estimation via diverse clustering techniques. Despite the experiment's limitations due to a small sample size and altered mobility patterns resulting from the COVID-19 pandemic, clustering algorithms (both distance- and density-based) successfully yield meaningful outcomes. The results include the identification of travel purposes, such as trips to home with or without overnight stays, trips to occasional destinations, commutes to work, trips to holiday stays, and more. These preliminary yet promising findings suggest that machine learning holds significant potential in mobility analysis, and it could feasibly be employed to estimate big-data-driven demand matrices, offering a higher degree of disaggregation and consequently enhancing the quality of transport modeling practices.