← AI Product Sense / 24
hardNewGoogleMetaSpotify

How would you launch recommendations when both users and items have little interaction history?

Try it in the practice workspaceDraft your answer before comparing it with the rubric.

Separate new-user and new-item problems, design a useful first session, and test whether early relevance survives beyond onboarding.

Updated Oct 2026 · Original practice questions with worked answers and teaching rubrics. Our editorial policy explains the sources, review process and limits.

Case briefRead the inputs, then make your call

A learning app needs useful recommendations for new users and newly published lessons. The randomized pilot is fictional.

Scenario inputs
Assignment500 new users per arm; keep original assignments for 14-day measurement.
First useful lessonBaseline: 120 users. Candidate: 170 users.
Return and useful completion within 14 daysBaseline: 90 users. Candidate: 80 users.
ConstraintsLittle interaction history; onboarding preferences are optional.

Your task. Design the recommendation and exploration approach. Interpret both outcomes and choose the next rollout decision.

Separate new-user and new-item problems, design a useful first session, and test whether early relevance survives beyond onboarding.

This reference answer is in Premium. Free signup opens other answers.

9 answers per topic instead of 5, and your progress kept · no cardor unlock all 420 remaining answers
UP NEXT ON YOUR JOURNEY
NOTES & DISCUSSION · 0

No comments yet. How would you have answered?