HOPE (High Order Profile Expansion) for the New User Problem on Recommender Systems

The new user problem is well-known in recommender systems and refers to the difficulty to provide accurate recommendations to a user who has just arrived to the system or who has provided very few ratings. Profile Expansion techniques intend to increase the size of the user profile by obtaining information about user preferences in distinct ways and have already been used to expand the information provided to recommendation algorithms and improve results. In this work, discussed in more detail at [1], we present the High Order Profile Expansion techniques, which combine in different ways the Profile Expansion methods. The results show 110% improvement in precision over the algorithm without Profile Expansion, and 10% improvement over Profile Expansion techniques.