Private Preferences, Public Rankings: A Privacy-Preserving Framework for Marketplace Recommendations
Guilherme Novaes Ramos, Ludovico Boratto, Mirko Marras · 2025
Protecting user privacy in recommender systems is crucial for fostering trust in marketplaces. In this paper, we propose a privacy-preserving framework that integrates public seller rankings into personalized recommendations without exposing sensitive user preferences. By utilizing ''seller representative users'' (encoding seller item rankings) and a novel recommendation mechanism, the framework preserves privacy while ensuring robust ranking accuracy. Our approach is validated on multiple use cases extracted from real-world datasets, showing its effectiveness across varying marketplace configurations. This framework is suited for real-world applications, such as e-commerce platforms, where it can enhance user trust, protect sensitive data, and improve engagement by transparently balancing personalization and privacy.