criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
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.
Stars
248
Forks
53
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...
ina-foss/twembeddings
Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and...