Estimating an e-scooter origin-destination model leveraging Yelp POI data for enhanced urban mobility insights

Abstract

E-scooter sharing programs have transformed urban mobility, providing an environmentally friendly solution for short-distance travel. Analyzing Origin-Destination (OD) travel behavior associated with e-scooter trip patterns is essential for effective urban planning, infrastructure enhancement, and policymaking. However, while numerous studies exist on developing OD travel behavior for passenger vehicles, there is a significant gap in developing such models for shared transportation modes like e-scooters. This study addresses this gap by estimating an OD model for e-scooter trips, integrating Points of Interest data from Yelp. E-scooter mobility data, traffic analysis zone (TAZ) shapefiles, and crowdsourced data from Louisville, KY, were collected to develop the OD model. Using a gravity-inspired random forest (RF) model, the e-scooter OD trip model was estimated. Findings revealed that total attraction and production have a high positive influence on trip distribution between TAZ, while the distance between TAZ has a significant negative impact. Additionally, the presence of bars, restaurants, shopping malls, and coffee shops strongly influences trip distribution between TAZ, whereas museums and parks have less influence. These results offer valuable insights for planning organizations, informing decisions on the relocation and optimization of e-scooter services to better meet the needs of urban commuters.