Data-Driven Prediction of Missing Links in Padova's Bike Lane Network

Cycling infrastructure is crucial for urban mobility, yet many cities struggle to keep up with the increasing demand for well-connected bike paths. This research, focused on Padova, Italy, proposes a data-driven method to identify and prioritize new bike routes. By integrating data from the Bike Sharing System, RideMovi, and modifying traditional centrality measures, a novel weighted benefit metric is introduced. Grounded in stress centrality, this metric considers both cyclist demand and the strategic importance of network components to prioritize infrastructure improvements effectively. The results indicate that central areas of Padova, especially around the train station and city center, need substantial upgrades. Key routes connecting the university and hospital are also prioritized, while peripheral areas are considered lower priority. This study provides actionable recommendations for enhancing bike network connectivity in high-demand zones. The analysis reveals that while the Component approach identifies broad infrastructure gaps, the Routing approach offers a more efficient solution by adding fewer kilometers of new paths, better aligning with actual cyclist demand. By combining centrality measures with real-world trip data, the research supports a targeted and effective strategy for urban bike network planning.