A Data-Driven Approach Supporting Location Decisions for Docking Stations in Bike-Sharing Systems

Blerina Spahiu, Daniela Briola, Riccardo Sartori, Giuseppe Vizzari

Abstract: Bike-sharing systems (BSSs) have become integral to urban mobility, improving accessibility, multimodality of transportation, and sustainability. This paper presents a novel approach to supporting decisions on the positioning of docking stations for dock-based BSSs by leveraging real-world historical mobility data to estimate mobility demand. In particular, we used taxi travels data as a proxy to generate a synthetic mobility demand dataset that was exploited to estimate the locations of a dock-based BSS stations through clustering techniques. This study aims to improve the practicality of station positioning. By addressing challenges related to station placement, this research offers insights into the practical implementation of data-driven approaches in BSS planning and management, advancing the efficiency and sustainability of urban bike-sharing systems.