Towards Increasing the Coverage of Interactive Recommendations

Abstract

An interactive recommender system pursues two somewhat contradictory goals. On one hand, the system should provide highly relevant recommendations with the best match to the overall user needs. On the other hand, the recommendations should be sufficiently diverse to cover a range of users' possible interests. Such recommendations increase chances that the user finds items that match their context while also informing the system which items are currently most important. In this paper, we present a ranking approach that balances the demands of relevance and coverage. We evaluate the approach on two problems, of advisor and movie recommendations, where the immediate needs of the user are likely to be diverse. Our approach considerably increases chances that the user finds relevant items in the first few steps of the recommendation dialog.