PRankAggreg: A fast clustering based partial rank aggregation

Abstract

When the input are multiple users’ top-m rankings, aggregating or integrating them into an order sequence (pRankAggreg) provides an interesting and classic research area that can be applied to information search, group recommendation, and web guidance, etc. Since the Kemeny optimal rule based rank aggregation is NP-hard, it poses a great challenge to efficient calculation of such joint ranking. In order to solve this problem, we put forward a novel user similarity measure according to users’ partial rankings, and this measure has good properties which can be used in a clustering method. Then, we design a fast strategy to determine whether two users are clustered together or not under a given similarity threshold. Finally, according to the result of clustering, we propose a novel partial rank aggregation method, pRankAggreg, which is a combination of partial rankings. A number of experiments on real datasets have shown that the methods presented in this paper outperform other existing algorithms.