criteo-research/CausE

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

48
/ 100
Emerging

This project helps build more accurate product recommendation systems for users by accounting for how product exposure influences their preferences. It takes historical user interaction data with products (like MovieLens or Netflix datasets) and generates refined 'embeddings' that represent both users and products, enabling better recommendations. E-commerce managers, content strategists, and data scientists focused on personalization would use this.

248 stars. No commits in the last 6 months.

Use this if you need to build or evaluate a recommendation system where you suspect that the way products are shown to users (exposure bias) is affecting the accuracy of your recommendations.

Not ideal if you are looking for a plug-and-play recommendation system solution without understanding the underlying causal inference principles, or if you don't have historical user-product interaction data.

e-commerce recommendation-systems personalization causal-inference user-engagement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

248

Forks

53

Language

Python

License

Apache-2.0

Last pushed

Oct 24, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/criteo-research/CausE"

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