Seminar Details
2008-04-15 (14.00) : Iterative filtering for a dynamical reputation system
At Euler building
Organized by Mathematical Engineering
Speaker :
de Kerchove D'Exaerde, Cristobald
Abstract :
I 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 nxm
evaluation matrix with a certain sparsity pattern. From this
evaluation matrix we give a nonlinear formula to define the
reputation of raters and objects. I also provide an iterative
algorithm that superlinearly converges to the unique vector of
reputations and this for any evaluation 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.