Iterative Filtering for a Dynamical Reputation System

The paper introduces a novel iterative method that assigns a rep- utation to n +m items: n raters and m objects. Each rater evaluates a subset of objects leading to a n m rating matrix with a certain sparsity pattern. From this rating matrix we give a nonlinear formula to dene the reputation of raters and objects. We also provide an iterative algorithm that superlin- early converges to the unique vector of reputations and this for any rating matrix. In contrast to classical outliers detection, no evaluation is discarded in this method but each one is taken into account with dierent weights for the reputation of the objects. The complexity of one iteration step is linear in the number of evaluations, making our algorithm ecient for large data set. Experiments show good robustness of the reputation of the objects against cheaters and spammers and good detection properties of cheaters and spam- mers.