hardDesignScenarioMidSeniorStaff
The recommender is good for users with history and useless for the ones who just signed up. What do you serve them?
Serve context instead of history: popularity conditioned on the country, device and referrer you already have, then re-rank on the first two clicks of the session with a model that needs no user identity. Reserve slots for exploration, and segment every offline metric by history length, because a metric averaged over users with history cannot see this cohort at all.
7 min readUpdated 2026-08-15
Answer
Short answer
For a cold-start recommender, serve contextual popularity first: country, device, referrer, time and entry page are useful before a user has history. Then re-rank from in-session clicks with a model that does not require a stored user embedding. Measure the cold cohort separately, because aggregate recommender metrics are dominated by users who already have history.
Was this answer helpful?
Likely follow-ups
- Where exactly do you put the switch between the cold path and the personalised model, and how do you find that point?
- Item cold start is worse than user cold start. Why, and what breaks the loop?
- You want three onboarding questions. How do you decide which three, and what do you do with the users who skip them?
- A bandit is exploring and a product manager says the results look worse. What do you show them?
Related questions
- How do you handle cold start for a brand new user and a brand new item?hardAlso on cold-start and recommenders5 min
- You are building a support assistant over a knowledge base that changes every week. RAG or fine-tuning, and how do you decide?mediumAlso on evaluation5 min
- Your RAG system cannot answer a question whose answer is definitely in the documents. Where is the fault?hardAlso on evaluation4 min
- You are shipping an LLM feature and there is no evaluation set. How do you build one?hardAlso on evaluation5 min