A market-based approach to address the new item problem

In this paper we propose a market-based approach for seeding recommendations for new items in which publishers bid to have items presented to the most influential users for each item. Users are able to select (or not) items for rating on an earn-per-rating basis, with payment given for providing a rating regardless of whether the rating is positive or negative. This approach reduces the time taken to obtain ratings for new items, while encouraging users to give honest ratings (to increase their influence) which in turn supports the quality of recommendations. To support this approach we propose techniques for inferring the social influence network from users' rating vectors and recommendation lists. Using this influence network we apply existing heuristics for estimating a user's influence, adapting them to account for the new items already presented to a user. We also propose an extension to Chen et al.'s Degree Discount heuristic [Chen et al. 2009], to enable it to be used in this context. We evaluate our approach on the MovieLens dataset and show that we are able to reduce the time taken to achieve coverage, while supporting the quality of recommendations.