Your question is TikTok Recommendation within Followed Circle. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
Design a recommendation algorithm for TikTok suggesting videos to users within their followed circle.
Asked in the phone screen stage. Discuss requirements, metrics, and the experiment goal. Reported follow-ups: How will matrix factorization scale to 1 billion users? How would you evaluate offline and online performance?
Address the recommendation objective, candidate generation and ranking approach, matrix factorization scalability, data and feature pipelines, serving choices, evaluation, experimentation, and failure modes. State which assumptions require clarification, including traffic, latency, freshness, and available interaction data.
