factual
A/B Tests Yield Causal But Black-Box Results
Random assignment lets tech firms separate correlation from causality almost perfectly, so they can act on a causal effect (e.g., dark blue brings users back more) even without understanding why; with often two black-box algorithms, you learn one is better and use it without knowing the mechanism.
factualpending
Speaker
Susan AtheyEvidence Quote
“they are able to separate correlation from causality almost perfectly.”
Created: 6/13/2026, 12:14:45 AM
Your notes
Loading notes...