Design a feed ranking system
Quick Overview
This question evaluates a candidate's competency in designing end-to-end machine-learning-based feed ranking systems, including setting ranking objectives, candidate generation and filtering, feature design, model training and serving, and operational concerns like freshness, diversity, and scalability.
Uber
Mar 1, 2026, 12:00 AM
Machine Learning Engineer
Technical Screen
ML System Design
2
0
Design a machine-learning-based feed ranking system for a consumer product. The system should rank candidate posts or items for a user's home feed in real time.
Discuss:
- Product goals and ranking objectives
- Online and offline metrics
- Candidate generation, filtering, ranking, and re-ranking stages
- Features and data sources
- Model training and serving architecture
- Handling freshness, diversity, spam, and cold start
- Experimentation, monitoring, and failure modes
- Latency, scalability, and reliability constraints
Solution
Show