mediumScenarioCase StudyMidSeniorStaff
Daily active users dropped 15% week over week. How do you diagnose it?
4 min readUpdated 2026-08-15
Answer
Short answer
Rule out instrumentation before behaviour, then segment along the dimensions that isolate a cause — platform, geography, cohort, and acquisition channel — to distinguish a broad drop from a concentrated one, since those have entirely different explanations.
Was this answer helpful?
Likely follow-ups
- It is isolated to Android in one country. What now?
- How would you tell a seasonal dip from a genuine regression?
- When would you decide it is not worth investigating further?
- What would you tell the CEO after two hours of investigation?
Related questions
- How would you improve a product you use every day?mediumAlso on product-sense and metrics6 min
- Your A/B test was configured for a 50/50 split but the data shows 53/47 across two million users. The result is significant and positive. What do you do?hardAlso on metrics5 min
- Name a product decision you think is bad. Now tell me why the team that made it might have been right.mediumAlso on product-sense5 min
- A competitor has just shipped the feature at the top of your roadmap. How do you respond?mediumAlso on segmentation5 min