This article was accepted into the 5th AAAI Workshop on Privacy-Preserving artificial intelligence.
Personalized recommendations form an important part of today's Internet ecosystem, helping artists and creators reach interested users and discover new and engaging content. However, many users today are skeptical of platforms that personalize recommendations, in part due to historically negligent treatment of personal data and data privacy. Now, companies that rely on personalized recommendations are entering a new paradigm, in which many of their systems must be overhauled to put privacy first. In this paper, we propose an algorithm for personalized recommendations that facilitates accurate and differentially private measurement. We consider advertising as an example application and conduct offline experiments to quantify how the proposed privacy-preserving algorithm affects key metrics related to user experience, advertiser value, and platform revenue in comparison. with both non-custom (private) and non-custom endpoints. Private and custom implementations.
