vdblm/CausalPFN

CausalPFN: Amortized Causal Effect Estimation via In-Context Learning

47
/ 100
Emerging

This project helps data scientists, machine learning engineers, and researchers quickly understand how different actions (treatments) truly impact outcomes. It takes your observational data, including features, treatments, and outcomes, and efficiently estimates both individual-level (CATE) and average-level (ATE) causal effects, even quantifying their uncertainty. The output helps you make more informed, personalized decisions.

Use this if you need to rapidly estimate causal effects from various datasets without retraining a model for each new scenario, especially in applications like personalized marketing or A/B testing analysis.

Not ideal if you primarily work with very small datasets or require highly interpretable, simple causal models that don't rely on complex deep learning architectures.

causal-inference uplift-modeling marketing-analytics personalized-decision-making A/B-testing
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

91

Forks

11

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

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

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