Build an MMM you can trust — calibrate it with experiments

Causal inferenceHard

Problem. You're building a media mix model to allocate the marketing budget. What makes an MMM untrustworthy, and how do you build one you can rely on?

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.