RecList/reclist
Behavioral "black-box" testing for recommender systems
This tool helps machine learning engineers and data scientists rigorously test their recommendation systems. You feed it your recommendation model's outputs and relevant dataset information, and it provides a comprehensive report on how well your system behaves in various real-world scenarios, beyond just standard accuracy metrics. It's designed for anyone building or deploying recommendation engines who needs to ensure their models are robust and fair.
472 stars. No commits in the last 6 months.
Use this if you build or manage recommendation systems and need to systematically check their behavior for issues like recommending rare items, handling new users, or making unexpected cross-recommendations.
Not ideal if you are looking for a tool to build or train recommendation models themselves, as this focuses solely on evaluating existing systems.
Stars
472
Forks
24
Language
Python
License
MIT
Category
Last pushed
Aug 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RecList/reclist"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
meta-pytorch/torchrec
Pytorch domain library for recommendation systems
recommenders-team/recommenders
Best Practices on Recommendation Systems
hongleizhang/RSPapers
RSTutorials: A Curated List of Must-read Papers on Recommender System.
kakao/buffalo
TOROS Buffalo: A fast and scalable production-ready open source project for recommender systems
google-research/recsim
A Configurable Recommender Systems Simulation Platform