PARS: Peers-aware Recommender System

The presence or absence of one item in a recommendation list will affect the demand for other items because customers are often willing to switch to other items if their most preferred items are not available. The cross-item influence, called “peers effect”, has been largely ignored in the literature. In this paper, we develop a peers-aware recommender system, named PARS. We apply a ranking-based choice model to capture the cross-item influence and solve the resultant MaxMin problem with a decomposition algorithm. The MaxMin model solves for the recommendation decision in the meanwhile of estimating users’ preferences towards the items, which yields high-quality recommendations robust to input data variation. Experimental results illustrate that PARS outperforms a few frequently used methods in practice. An online evaluation with a flash sales scenario at Taobao also shows that PARS delivers significant improvements in terms of both conversion rates and user value.