User Segmentation Based on Travel Regularity in E-Scooter Sharing Service

Abstract

The dockless e-scooter sharing service is rapidly spreading, replacing existing transportation, and improving last-mile accessibility. User segmentation with travel regularity and segment-level behavior analysis, which are already conducted in public transit, also benefits e-scooter sharing service to enhance service quality and increase usage. In this work, we group e-scooter users according to their travel regularity and identify each group’s usage characteristics. Through the dockless e-scooter usage data, as operated in six cities in South Korea, travel regularity measured by users’ repetitive departure time and destination is discovered and spatiotemporal usage patterns are identified. We divide e-scooter users into three groups by type of travel regularity: irregular user, spatially regular user, and regular user. Regular users more frequently use e-scooters, travel shorter distances, and walk longer distances to find an e-scooter than other groups. It is also revealed that the use in morning peak hours only occurs in the regular user group. By decomposing the temporal patterns of spatially regular and regular users, we discover that spatially regular users are composed of daytime, evening peak, and nighttime users. In contrast, regular users are composed of morning peak, evening peak, and lockdown (restriction in response to COVID-19 pandemic) peak users. This research suggests user segmentation based on travel regularity in e-scooter sharing services, enabling multiple strategies to be drawn to retain users with high regularity and convert users with low regularity to regular users.