TL;DR — Product Recommendation

Design a product recommendation system for an e-commerce platform that serves personalized product suggestions to hundreds of millions of users. The system must combine collaborative filtering (users who bought X also bought Y), content-based features (product attributes), and real-time behavioral signals (current session clicks) to rank recommendations. Key features: Personalized product recommendations on homepage, PDP, and cart. Two-stage pipeline: candidate generation (1000s) then ranking (top 20).