AWS Certified Solutions Architect – Associate (SAA-C03) — Question 425
An ecommerce company wants to use machine learning (ML) algorithms to build and train models. The company will use the models to visualize complex scenarios and to detect trends in customer data. The architecture team wants to integrate its ML models with a reporting platform to analyze the augmented data and use the data directly in its business intelligence dashboards.
Which solution will meet these requirements with the LEAST operational overhead?
Answer options
- A. Use AWS Glue to create an ML transform to build and train models. Use Amazon OpenSearch Service to visualize the data.
- B. Use Amazon SageMaker to build and train models. Use Amazon QuickSight to visualize the data.
- C. Use a pre-built ML Amazon Machine Image (AMI) from the AWS Marketplace to build and train models. Use Amazon OpenSearch Service to visualize the data.
- D. Use Amazon QuickSight to build and train models by using calculated fields. Use Amazon QuickSight to visualize the data.
Correct answer: B
Explanation
Amazon SageMaker is a fully managed service designed for building, training, and deploying machine learning models with minimal operational overhead, while Amazon QuickSight natively integrates with SageMaker to visualize augmented data directly in BI dashboards. Using AWS Glue ML transforms or custom marketplace AMIs requires significantly more management and operational effort to build and maintain. QuickSight calculated fields are not designed for training complex machine learning models, making Option B the most efficient and appropriate solution.