skip to Main Content
Comet Launches Kangas, an Open Source Data Analysis, Exploration and Debugging Tool for Machine Learning.

Resources for building better recommender systems


Building recommenders isn’t always easy. With input from Jacopo Tagliabue, Ronay Ak from Nvidia, and Serdar Kadioglu from Fidelity, here’s a list of resources that can help.

Learn more from the webinar on The Era of Hyper-Personalization: Building Better Recommender Systems and be sure to join the Comet ML Slack community for any questions!


Nvidia Merlin An open source framework for building high-performing recommender systems

RecList An open source library for behavioral, “black-box” testing for recommender systems

Fidelity Mab2Rec An open source framework for building contextual multi-armed bandits recommenders

RecSys Reproducibility Paper at TMLR’22 D. Kilitçioğlu, S. Kadıoğlu, Non-Deterministic Behavior of Thompson Sampling with Linear Payoffs and How to Avoid It, Transactions on Machine Learning Research (TMLR) 2022

Association for Computing Machinery (ACM) Terminology on Reproducibility
Contrastive language and vision learning of general fashion concepts
Companies, people and communities to follow


Avatar photo

Yasmeen Kashef

Back To Top