Real-time in-venue cognitive recommendations to user based on user behavior

User behaviors are monitored, by machine logic, during a visit to a venue by a user, the user behaviors associated with user interactions with items in the venue, a location of the items being tracked. In real-time, based at least in part on the user behaviors and the items, a subsequent behavior of the user is predicted by machine logic. Cognitive recommendations are provided by machine logic to the user in real-time during the visit, corresponding to additional items based at least in part on the predicted behaviors and the items. Machine learning is used to train a system for facilitating the noted aspects, as well as to update training.