Design Place Recommendation System
MetaMachine Learning Engineer · Onsite
Last updated
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.
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
Solution walkthrough is for members
Get the full walkthrough with reference code and complexity analysis, plus Kitty Coach at 300 messages a day. Hints, the code runner and community answers stay free.