Experimentation

CUPED

Controlled-experiment Using Pre-Experiment Data: regressing out each user's pre-period metric value to reduce variance.

Why interviewers ask about it

Cuts variance 30–50% for retention-style metrics - equivalent to a free 43–100% more traffic. Naming it is a strong senior signal.

The probability of detecting a true effect of a given size. Sample size n ≈ 16·p(1−p)/δ² per arm at 80% power, α = 0.05.

This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.