Q49 — AWS AIF-C01 Ch.1

Question 49 of 100 | ← Chapter 1

A company is building an ML model to analyze archival data. The company must run inference on large datasets—multiple gigabytes in size—and does not require immediate access to model prediction results. Which Amazon SageMaker inference option meets these requirements?

• A. Batch transform ✓
• B. Real-time inference
• C. Serverless inference
• D. Asynchronous inference

Correct Answer: A. Batch transform

Explanation

This question tests understanding of Amazon SageMaker inference options. Batch transform is designed for offline, high-throughput inference on large volumes of data stored in Amazon S3, producing predictions asynchronously without requiring low-latency responses—perfectly matching the scenario of multi-GB archival datasets and non-immediate result needs. Real-time inference is optimized for low-latency, interactive requests. Serverless inference offers automatic scaling and pay-per-use pricing but targets variable, event-driven workloads—not bulk archival processing. 'Asynchronous inference' is not a standard SageMaker inference option (though batch transform operates asynchronously, it is the designated service for this use case). Therefore, option A is correct.