User participation game in collaborative filtering

Collaborative filtering (CF) is widely used in recommendation systems. A user can get good recommendations only when both the user himself/herself and other users actively participate, i.e. providing sufficient rating data. However, due to the rating cost, rational users tend to provide as few ratings as possible. Therefore, there exists a trade-off between the rating cost and recommendation quality. In this paper, we model the interactions among users as a game in satisfaction form and study the corresponding equilibrium, namely satisfaction equilibrium (SE). Considering that accumulated rating data are used for recommendation, we design a behavior rule which allows users to achieve a SE via iteratively rating items. Experimental results based on real data demonstrate that, if all users have moderate expectations for recommendation quality and satisfied users are willing to provide more ratings, then all users can get satisfying recommendations without providing too many ratings. The SE analysis of the proposed game in this paper is helpful for designing mechanisms to encourage user participation.