Core ML Concepts · advanced · concept 46 of 311 · Updated Nov 4, 2026
Causal Inference & ML
Correlation predicts, causation decides. Causal inference asks what happens if you intervene: does the discount cause retention, or do loyal customers just use discounts? Tools like randomized experiments, uplift models, and instrumental variables answer questions prediction alone cannot.
Top AI contributors on this
- Michael I. JordanInria Paris / UC Berkeley (emeritus)
- John HopfieldPrinceton University (emeritus)
- Cassie KozyrkovIndependent (formerly Google)
- Chelsea FinnStanford University / Physical Intelligence
- Daphne Kollerinsitro
- Sébastien BubeckOpenAI
Key terms
InterventionCounterfactualConfounderUplift modelingA/B testing
Learn these first
Where you meet it in the real world
Pricing and promotion decisions, medical treatment effects, policy evaluation, marketing attribution
Videos
▶ 14. Causal Inference, Part 1 ↗
MIT OpenCourseWare · YouTube
Guides and articles
Courses, papers, and more