A company is running a machine learning prediction service that generates 100 TB of predictions every day. A Machine Learning Specialist must generate a visualization of the daily precision- recall…

Question

Options

• ARun daily Amazon EMR workflow to generate precision-recall data, and save the results in
• BGenerate daily precision-recall data in Amazon QuickSight, and publish the results in a
• CRun a daily Amazon EMR workflow to generate precision-recall data, and save the results in
• DGenerate daily precision-recall data in Amazon ES, and publish the results in a dashboard shared

• A
  4% (1)
• B
  22% (5)
• C
  61% (14)
• D
  13% (3)

Explanation

Processing 100 TB of daily predictions requires a distributed compute framework - Amazon EMR (Elastic MapReduce) handles this scale efficiently using Spark or Hadoop. Saving results to Amazon S3 after EMR processing is a standard, low-effort pattern. Amazon QuickSight can then connect directly to S3 data, auto-generate precision-recall visualizations, and publish read-only dashboard links to the Business team with minimal coding. Option A likely differs in storage target (e.g., HDFS), making sharing harder. Option B suggests generating precision-recall data inside QuickSight itself, which is not how QuickSight works - it visualizes data, not computes ML metrics. Option D uses Amazon Elasticsearch (now OpenSearch), which adds operational overhead compared to the S3+QuickSight pattern.

No community discussion yet for this question.