Workshop on Offline Evaluation for Recommender Systems

Recommender systems are notoriously hard to evaluate offline due to their interactive and dynamic nature. This workshop will re-visit the problem of designing metrics for recommendations and optimizing for them. Topics include (but are not limited to): offline-online correlation, counterfactual inference, reinforcement learning and open datasets.

This workshop will foster creative discussions within the community, spanning academic and industrial backgrounds. A dedicated poster area will be available during the workshop.

  • Thorsten Joachims, Information Science and Computer Science, Cornell University, USA
  • Adith Swaminathan, Deep Learning Technology Center, Microsoft Research, USA
  • Yves Raimond, R&D, Netflix, USA
  • Olivier Koch, R&D, Criteo, France
  • Flavian Vasile, R&D, Criteo, France


Sunday, Oct 7, 2018

Diamond Supporter
Platinum Supporters
Gold Supporters
Silver Supporters
Special Supporter