Iterative Filtering for a Dynamical Reputation System

TL;DR

This paper presents an iterative, nonlinear reputation system that effectively evaluates raters and objects, robustly detects cheaters, and converges efficiently regardless of rating matrix sparsity.

Contribution

It introduces a novel iterative algorithm with superlinear convergence for reputation assessment that accounts for all evaluations without discarding data.

Findings

Robust against cheaters and spammers

Efficient linear complexity per iteration

Effective detection of dishonest evaluators

Abstract

The paper introduces a novel iterative method that assigns a reputation to n + m items: n raters and m objects. Each rater evaluates a subset of objects leading to a n x m rating matrix with a certain sparsity pattern. From this rating matrix we give a nonlinear formula to define the reputation of raters and objects. We also provide an iterative algorithm that superlinearly 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 different weights for the reputation of the objects. The complexity of one iteration step is linear in the number of evaluations, making our algorithm efficient 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 spammers.