In this talk, I’ll be providing an overview of how we use ML algorithms to detect policy violative content on YouTube across all entity types: videos, comments, livestreams, engagements, etc and keep our community safe. ML algorithms are an essential part of YouTube Trust and Safety and I’m excited to share the lessons that we learned over many years while building, deploying and maintaining models at scale. Furthermore, I’ll be covering the unique sets of challenges for different entity types and product surfaces, like livestreams and shorts, which makes the problem domain particularly intriguing.