A privacy-preserving recommender system for mobile commerce

The problem of preserving the user's privacy in recommender systems for mobile commerce is faced in this work. We propose a novel framework to support private queries and evaluations, based on the concept of k-anonymity to protect the user's identity, which does not require a trusted third-party. Privacy is achieved via a dummy-user selecting algorithm based on grid-maps and a collaborative filtering algorithm based on the simple Bayesian classifier.