Users liking / interacting with things is a strong leading indicator of engagement and time spent, and you get it on a per-item basis. So you use those predictions heavily in deciding what to show people, but tune your model based on your larger scale metrics like time spent.
Users liking / interacting with things is a strong leading indicator of engagement and time spent, and you get it on a per-item basis. So you use those predictions heavily in deciding what to show people, but tune your model based on your larger scale metrics like time spent.