AWS Certified Machine Learning – Specialty — Question 215

A manufacturing company wants to monitor its devices for anomalous behavior. A data scientist has trained an Amazon SageMaker scikit-learn model that classifies a device as normal or anomalous based on its 4-day telemetry. The 4-day telemetry of each device is collected in a separate file and is placed in an Amazon S3 bucket once every hour. The total time to run the model across the telemetry for all devices is 5 minutes.

What is the MOST cost-effective solution for the company to use to run the model across the telemetry for all the devices?

Answer options

• A. SageMaker Batch Transform
• B. SageMaker Asynchronous Inference
• C. SageMaker Processing
• D. A SageMaker multi-container endpoint

Correct answer: A

Explanation

SageMaker Batch Transform is the most cost-effective option because it is designed for processing large datasets in a single batch, making it suitable for the company's hourly telemetry files. The other options, such as SageMaker Asynchronous Inference and multi-container endpoints, are better suited for real-time or interactive predictions, which would be more expensive and unnecessary for this batch processing scenario.