RUCAIBox/RecBole

A unified, comprehensive and efficient recommendation library

58
/ 100
Established

This project helps e-commerce managers, content strategists, and other product owners quickly test and compare different recommendation algorithms to suggest products, content, or services to users. You input existing user interaction data (like purchases, clicks, or views), and it outputs a working recommendation model. This is for professionals who need to build and evaluate effective recommendation systems.

4,307 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to research, benchmark, or develop new recommendation algorithms and want a comprehensive framework with many pre-implemented models and datasets.

Not ideal if you're looking for a low-code, drag-and-drop solution or a deployed, production-ready recommendation service.

e-commerce content-personalization algorithm-benchmarking recommender-systems user-engagement
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

4,307

Forks

732

Language

Python

License

MIT

Last pushed

Feb 24, 2025

Commits (30d)

0

Dependencies

16

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RUCAIBox/RecBole"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.