Abstract
One of the major challenges on Recommender Systems is how to predict users' preferences regarding contextual constraints in a group. There are situations which a user could be recommended with an appropriate item for one of their groups, but the same item may not be suitable when interacting with another user and/or group. We note that recommender systems should try to satisfy the group's demands, but it should also respect the user's individuality. We propose a conceptual architecture which uses additional information from users and items in order to build up users' profiling models according to a contextual constraint. The proposal is based on an existent hybrid recommender model that integrates user's information and item's factors into a generic latent factor model. One advantage of our model is the possibility to compute the bias on users' similarity according to the contextual constraints, that assist the group modeling, such as group of individuals who share the same content. The proposal represents the first steps towards the development of a group recommender system model, in order to introduce the concept of always-welcome recommendations.