Data Analytics in Free-Floating Carsharing: Evidence from the City of Berlin

Carsharing has emerged as an alternative to vehicle ownership and is a rapidly expanding global market. Particularly through the flexibility of free-floating models, car sharing complements public transport since customers do not need to return cars to specific stations. We present a novel data analytics approach that provides decision support to car sharing operators -- from local start-ups to global players -- in maneuvering this constantly growing and changing market environment. Using a large set of rental data, as well as zero-inflated and geographically weighted regression models, we derive indicators for the attractiveness of certain areas based on points of interest in their vicinity. These indicators are valuable for a variety of operational and strategic decisions. As a demonstration project, we present a case study of Berlin, where the indicators are used to identify promising regions for business area expansion.