Practice — Model Serving & Deployment (5 questions)

A social app wants to rank which of a user's pending notifications to surface first when they open the app, and also decide, throughout the day, whether a new notification is worth a push alert at all. There are 80 M daily active users and roughly 15 notification events per user per day.

1. Which inference mode(s) would you use for (a) ranking notifications when the app opens, and (b) deciding whether to push-alert a new event as it happens? Justify each.
2. Propose a hybrid design that reduces online cost without hurting freshness for either sub-problem.
3. What is the concrete risk of batch-scoring all 80 M users nightly for the "push or not" decision?