Matrix factorization techniques for context aware recommendation

TLDR

Context aware recommender systems (CARS) adapt recommendations to the specific situation in which items will be consumed. The paper proposes a novel context‑aware recommendation algorithm that extends matrix factorization. The algorithm models contextual factor interactions with item ratings by introducing additional model parameters into the matrix factorization framework. Experiments demonstrate that the method achieves results comparable to state‑of‑the‑art complex approaches, with lower computational cost and flexible granularity, and it has been applied to place‑of‑interest and music recommendation.

Abstract

Context aware recommender systems (CARS) adapt the recommendations to the specific situation in which the items will be consumed. In this paper we present a novel context-aware recommendation algorithm that extends Matrix Factorization. We model the interaction of the contextual factors with item ratings introducing additional model parameters. The performed experiments show that the proposed solution provides comparable results to the best, state of the art, and more complex approaches. The proposed solution has the advantage of smaller computational cost and provides the possibility to represent at different granularities the interaction between context and items. We have exploited the proposed model in two recommendation applications: places of interest and music.