Spatio-temporal mobility patterns of on-demand ride-hailing service users

Understanding individual mobility behavior is critical for modeling urban transportation. Different types of emerging data sources such as mobile phone records, social media posts, GPS observations, and smart card transactions have been used to reveal individual mobility behavior. In this paper, spatio-temporal mobility behaviors are reported using large-scale data collected from a ride-hailing service platform. Using passenger-level travel information, to characterize temporal movement patterns, trip generation characteristics, and distribution of gap time between consecutive trips are revealed. To understand spatial mobility patterns, we observe the spatial distribution of residences and workplaces, and the distributions of travel distance and travel time. Our analysis highlights the differences in mobility patterns of ride-hailing services users, compared to the findings of existing studies based on other data sources. The results show the potential of developing high-resolution individual-level mobility models that can predict the demand for emerging mobility services with high fidelity and accuracy.