Target Tracking in the recommender space - Toward a new recommender system based on Kalman filtering

International audienceWe assume that users and their consumptions of television programs are vectors in the multidimensional space of the categories of the resources. Knowing this space, we propose an algorithm based on a Kalman filter to track the user's profile and to foresee the best prediction of their future position in the recommendation space. From this prediction, we build a recommendation of contents