Ever wondered how Netflix knows what you'll watch next, or how YouTube always seems to know your taste before you do?
Recommendation systems now sit at the heart of how users discover content, products, and decisions across nearly every major platform — making them one of the highest-leverage areas for product and engineering teams to get right. This talk breaks down the full architecture of a scalable recommendation system: from data pipelines and modeling approaches (collaborative filtering, content-based filtering, neural networks) to business constraints, latency, feedback loops, and monitoring. Attendees will walk away with a practical framework for evaluating tradeoffs at every stage of building or scaling a recommender. If you're a PM, engineer, or technical lead working on personalization, ranking, or discovery, this session will give you a concrete checklist to bring back to your own systems.
