Who should get the discount? Estimating heterogeneous effects

Heterogeneous effectsHard

Problem. A subscription discount lifts conversion on average, but it's expensive (you're giving margin away). You suspect it only changes behavior for some viewers and is wasted on others. How do you find who 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 price change — how do you measure its effect?A Gifting experiment looks great — but is it just network spillover? →