UMAP: Urban Mobility Analysis Platform to Harvest Car Sharing Data

Car sharing is nowadays a popular transport means in smart cities. In particular, the free-floating paradigm lets the users look for available cars, book one, and then start and stop the rental at their will, within the city area. This is done by using a smartphone app, which in turn contacts a web-based backend to exchange information. In this paper we present UMAP, a platform to harvest data freely made available on the web to extract driving habits in cities. We design UMAP to fetch data from car sharing platforms in real time, and process it to extract more advanced information about driving patterns and user’s habits while augmenting data with mapping and direction information fetched from other web platforms. This information is stored in a data lake where historical series are built, and later analyzed using easy to design and customize analytics modules. We prove the flexibility of UMAP by presenting a case of study for the city of Turin. We collect car sharing usage data over 50 days, and characterize both the temporal and spatial properties of rentals, as well as users’ habits in using the service, which we contrast with public transportation alternatives. Results provide insights about the driving style and needs, that are useful for smart city planners, and prove the feasibility of our approach.