Causal Discovery | Inferring causality from observational data

🤝 Want your team maximizing Claude? I run 1:1 and team AI workshops for companies doing $1M+ per year: https://aibuilder.academy/yt/tufdEUSjmNI This is the final video in a three-part series on causality. In it, I sketch some big ideas from causal discovery, which aims to infer causal structure from data. I finish with a concrete example of doing causal discovery in Python. Series Playlist: https://www.youtube.com/playlist?list=PLz-ep5RbHosVVTz9HEzpI4d6xpWsc8rOa 📰 Read more: https://medium.com/towards-data-science/causal-discovery-6858f9af6dcb?sk=2134f5b56c1ce943afdfebbf9e1dcb45 💻 Example code: https://github.com/ShawhinT/YouTube-Blog/tree/main/causality/causal_discovery Resources: - The Book of Why by Judea Pearl: https://www.amazon.com/Book-Why-Science-Cause-Effect/dp/046509760X - Causal Discovery Review: https://www.frontiersin.org/articles/10.3389/fgene.2019.00524/full - Causal Discovery Toolbox: https://fentechsolutions.github.io/CausalDiscoveryToolbox/html/index.html Introduction - 0:00 Causal Discovery - 0:21 Forward/Inverse Problem - 1:09 3 Tricks of Causal Discovery - 2:28 Trick 1: Conditional Independence Testing - 2:32 Trick 2: Greedy Search of DAG Space - 5:01 Trick 3: Exploiting Asymmetries - 8:23 Trick-based Taxonomy - 10:34 Example: Causal Discovery with Census Data - 11:13 Closing remarks - 14:26