Real‑Time Nearby Places Recommendation System
Context
Design a mobile feature that recommends nearby places (e.g., restaurants, shops, attractions) to a user in real time as they move. The system should work globally, handle dense urban and sparse rural areas, respect user privacy, and scale to high QPS.
Requirements
-
Define objectives and success metrics.
-
Describe data sources: maps/POIs and user behavior.
-
Candidate generation using geospatial filtering.
-
Feature engineering: distance, popularity, personalization, context (time/weather).
-
Ranking model choice and training signals.
-
Cold‑start strategies for new users and new places.
-
Exploration vs. exploitation strategy.
-
Spam/fraud filtering.
-
Privacy considerations.
-
Latency/throughput budgets and system architecture.
-
Online A/B testing and monitoring plan.