Reward-Optimizing-Reco

Materials for the "Reward Optimizing Recommendation using Deep Learning and Fast Maximum Inner Product Search" tutorial delivered at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML '22) and the 28th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '22).

ECML - To run the notebooks on Google Colab:

• Part 1:

• Part 2:

• Part 3:

• ECML Slides

KDD - To run the notebooks on Google Colab:

• Part 1:

• Part 2:

• Slides

Authors : Imad Aouali, Amine Benhalloum, Martin Bompaire, Achraf Ait Sidi Hammou, Sergey Ivanov, Benjamin Heymann, David Rohde, Otmane Sakhi, Flavian Vasile, Maxime Vono

• Aouali et al., A Scalable Probabilistic Model for Reward Optimizing Slate Recommendation

• Sakhi et al., Fast Offline Policy Optimization for Large Scale Recommendation