Who should get the promo? Estimating heterogeneous effects

Heterogeneous effectsHard

Problem. A promo lifts orders on average but is expensive. You suspect it only changes behavior for some customers. How do you find whom to target?

Before you reveal: say your answer out loud, as if you were in the real interview — get your reasoning across clearly first. There is no single correct answer: reading what the interviewer is really after and defending your own thinking is what makes an answer strong.

← You can't A/B a marketing channel — measure its incrementalityYour order-rate experiment is underpowered — how do you fix it? →