Recommender systems provide personalized advice to their users about content or products that they might enjoy. To achieve this feat, recommender systems leverage the opinions of a large pool of users, who are similar to the users receiving advice.

We investigate the performance of recommender system algorithms in the domains of wine and movies, and assess the potential influence of different individuals (amateurs and seasoned critics alike) in shaping the advice provided by recommender systems to their users.

THIS PROJECT IS PART OF THE AI-PARTNERS NETWORK
Team
Pantelis Analytis
Pantelis Analytis
Ophelia Deroy
Ophelia Deroy
Bahador Bahrami
Bahador Bahrami
Karthikeya Kaushik
Karthikeya Kaushik