Once a week the compost office drops a single large CSV of well readings and wants a scored file back in the same bucket. Nobody will call an API per row, and no endpoint should sit around between runs. Which serving mode fits?
Select an answer to reveal the explanation.
Short Explanation
Once a week the compost office drops one CSV and wants a scored file back in the same bucket. Batch transform scores a file already on S3. A real-time or serverless endpoint should not sit idle between drops, and Personalize is not that transform.
Full Explanation
SageMaker batch transform is the offline inference path when the file set is already on S3 and no per-row API is required. A persistent real-time or serverless endpoint should not sit idle between weekly drops. Personalize is not batch transform.