Interview: design a recommender for a new streaming service.
hardAnswer
- (1) Cold-start heavy: no history.
- Start with content-based recsys (title/description embeddings, genre, actors → cosine similarity to what user selects).
- (2) Log implicit signals from day 1 (plays, completes).
- (3) After N interactions, hybrid: two-tower CF + content features.
- (4) Diversity: MMR reranking + calibration.
- (5) Bandits for exploration of new content.
- (6) Evaluate: retention, watch time (long-term), CTR/CVR (short-term), diversity, novelty.
- (7) A/B test each change.
Check yourself — multiple choice
- Just CF
- Cold-start via content-based + log implicit + hybrid two-tower + MMR diversity + bandits exploration + retention/watchtime/CTR/diversity metrics + A/B
- Random
- Not real
New streaming recsys: content cold-start → hybrid + bandits + diversity + retention KPIs.
#interview#applications
Practise Unsupervised Learning
214 interview questions in this topic.
Related questions
- Interview: 'you're asked to segment 10M customers — how?'
- Interview: 'design an unsupervised fraud detection system'.
- Interview: cluster 5M e-commerce customers for a marketing campaign.
- Interview: production fraud detector — daily volume 10M, current FN too high.
- Interview: your model's accuracy dropped 15% overnight — how do you diagnose?
- Interview: you must ship an embedding service serving 100M vectors, 10ms p95 latency.