A Data-Driven Based Dynamic Rebalancing Methodology for Bike Sharing Systems

Mobility in cities is a fundamental asset and opens several problems decision making the creation of new services for citizens. In last years, transportation sharing systems have been continuously growing. Among these, bike became commonly adopted. There exist two different categories systems: station-based free-floating services. this paper, we concentrate our analyses on systems. Such require periodic rebalancing operations to guarantee good quality service system usability by moving bicycles from full stations empty stations. particular, propose dynamic bicycle methodology based frequent pattern mining its implementation. The extracted patterns represent unbalanced situations among nearby They are used predict upcoming critical statuses plan most effective using an entirely data-driven approach. Experiments performed real data Barcelona show effectiveness proposed