Manipulation Robustness of Collaborative Filtering Systems - Computer Science > LearningReport as inadecuate




Manipulation Robustness of Collaborative Filtering Systems - Computer Science > Learning - Download this document for free, or read online. Document in PDF available to download.

Abstract: A collaborative filtering system recommends to users products that similarusers like. Collaborative filtering systems influence purchase decisions, andhence have become targets of manipulation by unscrupulous vendors. We providetheoretical and empirical results demonstrating that while common nearestneighbor algorithms, which are widely used in commercial systems, can be highlysusceptible to manipulation, two classes of collaborative filtering algorithmswhich we refer to as linear and asymptotically linear are relatively robust.These results provide guidance for the design of future collaborative filteringsystems.



Author: Xiang Yan, Benjamin Van Roy

Source: https://arxiv.org/







Related documents