Getting recommender systems to think outside the box

We examine the case of over-specialization in recommender systems, which results from returning items that are too similar to those previously rated by the user. We propose Outside-The-Box (OT B) recommendation, which takes some risk to help users make fresh discoveries, while maintaining high relevance. The proposed formalization relies on item regions and attempts to identify regions that are underexposed to the user. We develop a recommendation algorithm which achieves a compromise between relevance and risk to find OT B items. We evaluate this approach on the MovieLens data set and compare our OT B recommendations against conventional recommendation strategies. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval General Terms Algorithms, Experimentation Keywords otb, outside the box, diversity, serendipity, recommendation

• Type: Conference
• Year: 2009
• Where: RECSYS
• Authors: Zeinab Abbassi, Sihem Amer-Yahia, Laks V. S. Lakshmanan, Sergei Vassilvitskii, Cong Yu
• Keywords: Control Systems, Conventional Recommendation Strategies, OT B, Recommendation Algorithm, RECSYS 2009