Test a New Feature at Its Natural Product Placement
LinkedInData Scientist · Onsite
Last updated
Design a feature launch experiment that separates natural-placement availability, discoverability, promotional exposure, and downstream product value.
Test a New Feature at Its Natural Product Placement
Design an experiment for a new feature. Explain why initially evaluating it in its natural product placement can be useful before increasing its exposure. Define what effect the first experiment estimates and how you would separately evaluate later changes in prominence or promotion.
Hints
Hint 1
Define the policy being tested: A feature with a large promotional placement is a different treatment from the same feature in its ordinary location.
Follow-up questions
- Can low exposure make a natural-placement experiment inconclusive?
- Why is comparing users who discovered the feature with users who did not a biased causal comparison?
Solution walkthrough is for members
Get the full walkthrough with reference code and complexity analysis, plus Kitty Coach at 300 messages a day. Hints, the code runner and community answers stay free.