Ferry planners need a bunching-risk score for every stop by 06:00 from last night's AVL dump. The SLA is a completed file, not a sub-second UI call. Which deployment strategy fits?
Select an answer to reveal the explanation.
Short Explanation
Ferry planners need a bunching-risk file by 06:00 from last night's AVL dump. That is a batch or scheduled-transform strategy. A real-time endpoint is the wrong SLA, Rekognition is not an AVL dump, and a trainer is not overnight scoring.
Full Explanation
A completed morning file from a known dump is a batch or scheduled-transform deployment, even if someone casually says production inference. A real-time endpoint is the wrong SLA. Rekognition and a training job are not that overnight score.