The feature that wins in week one and fades by week four
Asked at Meta
A redesigned feed shows a large engagement lift in the first few days of an A/B test. By the end of the second week the lift has shrunk considerably. The team debates whether to ship based on the early number or the later one.
Explain the novelty (and primacy) effects, how to detect them, and how they should change your read of the experiment.
Your answer
This one is open-ended. Work it through, then check your reasoning against the full solution.