Session-based Recommendation and Reinforcement Learning
Staff - Faculty of Informatics
Date: 7 June 2023 / 15:30 - 16:30
USI Campus Est, room C1.05, Sector C
Speaker: Alexandros Karatzoglou, Research Scientist at Google Deepmind
Abstract:
Session-based recommender systems are the main type of recommendation algorithm deployed in industry at large scale, responsible for more than half of all impressed recommendations. A recommender system aims (or should aim) to provide recommendations (actions) to users (environment) with the objective of maximising the long-term user satisfaction (reward) with the system. RL is a natural fit for this task, In this talk I will introduce the main methods behind session-based recommenders and how RL is used currently to install desired properties to these models.
Biography:
Alexandros Karatzoglou is a Research Scientist at Google Deepmind (former Brain). He was previously the Scientific Director at Telefonica Research in Barcelona, Spain. His research focuses on Machine Learning for Recommender Systems. He received his PhD in Machine Learning from the Vienna University of Technology (TUWIEN). During his PhD he was a frequent visitor to the Statistical Machine Learning group at the ANU/NICTA in Canberra Australia. He is also the author of the core machine learning R package kernlab, and enjoys giving lectures on Machine Learning, Recommender Systems and Computational Statistics.
Host: Louis Kirsh, IDSIA
