MLS-C01 Question #268: Real Exam Question with Answer & Explanation

Question

A machine learning (ML) engineer at a bank is building a data ingestion solution to provide transaction features to financial ML models. Raw transactional data is available in an Amazon Kinesis data stream. The solution must compute rolling averages of the ingested data from the data stream and must store the results in Amazon SageMaker Feature Store. The solution also must serve the results to the models in near real time. Which solution will meet these requirements?

Options

• ALoad the data into an Amazon S3 bucket by using Amazon Kinesis Data Firehose. Use a
• BWrite the data directly from the data stream into SageMaker Feature Store as an online feature
• CConsume the data stream by using an Amazon Kinesis Data Analytics SQL application that
• DLoad the data into an Amazon S3 bucket by using Amazon Kinesis Data Firehose. Use a

Explanation

The solution requires real-time processing of a Kinesis data stream to compute rolling averages and store them in SageMaker Feature Store for near real-time model serving.

Common mistakes.

• A. Amazon Kinesis Data Firehose is primarily for delivering streaming data to destinations like S3, Redshift, or Splunk, and does not inherently perform real-time analytical computations like rolling averages on the fly before delivery.
• B. Writing data directly from a Kinesis data stream to SageMaker Feature Store does not allow for the computation of rolling averages, as SageMaker Feature Store is a repository, not a stream processing engine.
• D. Amazon Kinesis Data Firehose is primarily for delivering streaming data to destinations like S3, Redshift, or Splunk, and does not inherently perform real-time analytical computations like rolling averages on the fly before delivery.

Concept tested. Real-time stream analytics with Kinesis Data Analytics

Reference. https://docs.aws.amazon.com/kinesisanalytics/latest/sql/getting-started-create-app-kda.html

No community discussion yet for this question.