Design an A/B test for a recommendation algorithm
Last updated: October 14, 2025
Quick Overview
Design an experiment to test the impact of a redesigned homepage. Include sample size calculation, metrics, and analysis plan.
TikTok
October 14, 202544
15
3,033 solved
Design an experiment to test the impact of a redesigned homepage. Include sample size calculation, metrics, and analysis plan.
This analytics question from TikTok's Phone Screen tests your ability to think critically about data. The interviewer expects you to consider confounding variables, selection bias, and the difference between correlation and causation.
What the Interviewer Expects
- Design a rigorous experiment with proper randomization and sample size calculation
- Define primary and guardrail metrics with clear rationale
- Address novelty effects, network effects, and interference
- Segment results appropriately and identify heterogeneous treatment effects
- Propose follow-up analyses when results are ambiguous
Key Topics to Cover
How to Approach This
- Define success metrics carefully. A good metric is measurable, actionable, and aligned with business goals.
- Run experiments long enough to account for novelty effects and weekly seasonality.
- Use funnel analysis to identify where users drop off for maximum optimization impact.
- Segment results by key dimensions (platform, country, user cohort) to catch hidden patterns.
- Consider network effects and interference between treatment and control groups.
Possible Follow-up Questions
- How would you handle seasonality in your experiment?
- What if you discover a bug in the logging during the experiment?
- How would you handle interference between treatment and control?
Sharpen Your Skills on Codemia
Practice similar problems with our interactive workspace, get AI feedback, and track your progress.
Browse Analytics QuestionsSample Answer
Problem Setup
To assess the impact of a redesigned homepage on user engagement, we need to formulate a clear analytical question: 'Does the new homepage design increase the average daily time spent on the app per u...
Methodology
We will use a randomized controlled trial (RCT) design to compare the performance of the current homepage (control group) with the redesigned homepage (treatment group).
Sample Size Calculation:...
Submit Your Answer
