Machine Learning Street Talk Video posted an update
A perfect model can still get causality backwards
Why it mattersThis video explains why a model can predict outcomes perfectly yet still point to the wrong decision: patients receiving a medicine may be more likely to have a disease, but stopping the medicine would not cure it. Frank Hutter contrasts observation with intervention and connects the idea to causal machine learning, TabPFN, and foundation models for tabular data.
Discuss: How should causal machine learning distinguish a genuine treatment effect from the misleading pattern that patients receiving medicine may already be sicker?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.