ML System Design
How would you handle new users and new posts in a social-feed recommender with text and image content?
Ответить самому
Сначала сформулируйте ответ как на собеседовании, затем откройте разбор и оцените себя.
Короткий ответ
For new posts, use content embeddings, metadata and exploration buckets. For new users, use onboarding/profile/context, popularity by segment and controlled exploration until enough interaction history exists.
Полный разбор
New posts have no interaction history, so represent them through content: text embedding, image embedding, topic/category, author, language, freshness and safety signals. Route them through freshness and exploration pools so the system can collect initial feedback without flooding users.
New users need fallbacks before history exists. Use onboarding interests if available, coarse profile/context segments that are allowed for the product, geo/time/device context, global or segment popularity, and user-to-user similarity from non-sensitive profile features. Then quickly update a short-term profile from early positive and negative interactions.
Cold start should be measured. Track coverage for new posts, time to first impressions, new-user engagement, hide/report rate and diversity. Keep exploration bounded so it learns without damaging user trust.
Теория
Cold start is a controlled exploration and representation problem, not only a model problem.
Типичные ошибки
- Serve only global top-pop to every new user.
- Wait for interaction history before showing new posts.
- Use sensitive profile features casually.
- Ignore negative early feedback such as hides and skips.
Как отвечать на собеседовании
- Split the answer into new users and new items.
- Mention bounded exploration and fast profile updates.