Netflix deployed a machine learning recommendation system that personalizes the content each subscriber sees on their homepage, selecting which titles to surface and in what order based on that person's viewing history, search behavior, and patterns from similar users.

The system ingests terabytes of daily behavioral signals — including viewing duration, pause patterns, skip behavior, search queries, and device context — and combines collaborative filtering, deep learning, and graph-based models to generate ranked recommendations at sub-100ms latency for each user. Netflix's internal 'Hydra' multi-task model handles homepage ranking, search result ordering, and notification personalization simultaneously, using shared user and content representations. Netflix has publicly confirmed that approximately 80% of content viewed on the platform is driven by this recommendation system.