Modern recommender systems are trained to predict users’ potential future interactions from historical behavior data. During the interaction process, despite data coming user side, also generate exposure provide users with personalized recommendation slates. Compared sparse data, system much larger in volume since only very few exposed items would be clicked by user. In addition, privacy sensit...

• We compare 20 carsharing user groups in a medium-sized urban environment. Partial overlapping reveals interdependencies among the groups. The differ considerably their spatial and temporal usage behavior. Promoting with anticyclical behavior helps to balance occupation rates. of free-floating station-based differs several aspects. rapidly developing concept is an essential scalable part susta...