Can we trust the algorithms that recommend products online? Theory and practice of recommender systems.

Upon logging into their Netflix, Amazon or Spotify accounts, consumers are usually greeted with personalized recommendations on goods from the catalogue that they might enjoy or need. These recommendations are provided by algorithms, called recommender systems (RS), which use big data to predict consumer tastes. Recommender systems are extremely popular with on-line businesses as they help boost consumer engagement, a key driver of business retention and creation. I will present a stylized theoretical model of RS and (very preliminary) results from an experimental investigation with actual RS algorithms in synthetic environments.

Join at imt.lu/seminar