On Differentially Private Online Collaborative Recommendation Systems

TL;DR

This paper analyzes the balance between privacy and recommendation quality in online collaborative recommendation systems, providing theoretical bounds and a near-optimal algorithm within the differential privacy framework.

Contribution

It offers the first quantitative analysis of privacy-utility trade-offs in such systems, including a lower bound and a near-optimal algorithm.

Findings

Little trade-off between privacy and recommendation quality for non-trivial algorithms

Identifies key parameters influencing privacy bounds

Provides a near-optimal algorithm for privacy-preserving recommendations

Abstract

In collaborative recommendation systems, privacy may be compromised, as users' opinions are used to generate recommendations for others. In this paper, we consider an online collaborative recommendation system, and we measure users' privacy in terms of the standard differential privacy. We give the first quantitative analysis of the trade-offs between recommendation quality and users' privacy in such a system by showing a lower bound on the best achievable privacy for any non-trivial algorithm, and proposing a near-optimal algorithm. From our results, we find that there is actually little trade-off between recommendation quality and privacy for any non-trivial algorithm. Our results also identify the key parameters that determine the best achievable privacy.