Question

A retail analytics team has 12 months of accumulated sales records stored in Amazon S3. Once every night, they want to score the entire dataset with a trained model to generate a report for the next business day. There is no requirement for immediate, per-request responses, and no application waits synchronously for individual predictions. Which inference approach best fits this need?

Accepted Answer

Use SageMaker Batch Transform to score the full S3 dataset in a scheduled job

Answer

Deploy a real-time SageMaker endpoint and send each record as an individual API call

Answer

Retrain the model each night so predictions are embedded in the training output

Answer

Configure a serverless real-time endpoint with auto scaling to handle each record