Design Place Recommendation System
Company: Meta
Role: Machine Learning Engineer
Category: ML System Design
Difficulty: medium
Interview Round: Onsite
Design a machine learning system for a maps or local-discovery product that recommends places a user may want to visit. The system should provide personalized suggestions such as restaurants, cafes, parks, and attractions using signals including user history, current location, time of day, search behavior, map interactions, social or popularity signals, and place metadata.
Discuss:
- Product goals and success metrics
- How to define training labels and prediction targets
- Data sources and feature engineering
- Candidate generation and ranking architecture
- Handling cold start for new users and new places
- Real-time context and latency constraints
- Online serving, feedback loops, and experimentation
- Risks such as popularity bias, feedback loops, spam, and fairness across places and regions
Overview: This question evaluates machine learning system design skills specific to recommender systems, including competencies in feature engineering, candidate generation and ranking, data engineering, online serving, latency and real-time context handling, evaluation metrics, and fairness/bias mitigation.