Meta·Data Scientist·Onsite - System Design / Architecture
Jun 2026
A deep system design interview at Meta for a Data Scientist role, focused entirely on building a hashtag recommendation system for News Feed end-to-end. The question was massive and covered everything from label construction to safety filters, so it felt less like one question and more like ten back-to-back. Brutal but fair.
- How would you define the prediction target and unit of observation for a hashtag recommendation system in a social media News Feed? How do you construct positive and negative labels from logs without introducing selection bias?
- What candidate generation sources would you use for hashtag recommendations, and how do you prevent popularity bias from dominating the results?
- Describe at least ten concrete features you would use in a logistic regression ranker for hashtag recommendations, covering user affinity, post relevance, temporal signals, and locale.
- Why start with a calibrated logistic regression instead of a deeper model? Walk through your regularization choices, how you'd handle class imbalance, and how you'd prevent data leakage.
- How would you check and correct model calibration, and how would you set display thresholds per user cohort or surface? What about exploration rates for new hashtags?
- What offline metrics would you use to evaluate the ranker, and how would you account for position bias in historical data when estimating top-k ranking quality?
- How would you design the online experiment for this feature? Cover randomization unit, guardrail metrics, primary outcomes, novelty effect detection, and stopping criteria.
- How do you handle cold start for new hashtags and new users, and how do you detect and respond to concept drift in hashtag popularity?
- What safety and policy risks exist with hashtag recommendations, and how would you handle real-time filtering and fairness across languages and regions?
- How would you translate the logistic regression coefficients into actionable product insights, for example around diminishing returns from showing too many hashtags or language mismatch penalties?
“This is where I spent the most time and probably the most words.” The rest of the author's notes on Data Scientist interview at Meta, Onsite - System Design / Architecture round, covers how they worked through the question, what the panel pushed back on, and what they would do differently.
View Post