AWS Certified Machine Learning – Specialty — Question 265

A company has a podcast platform that has thousands of users. The company implemented an algorithm to detect low podcast engagement based on a 10-minute running window of user events such as listening to, pausing, and closing the podcast. A machine learning (ML) specialist is designing the ingestion process for these events. The ML specialist needs to transform the data to prepare the data for inference.

How should the ML specialist design the transformation step to meet these requirements with the LEAST operational effort?

Answer options

Correct answer: C

Explanation

Using Amazon Kinesis Data Streams for ingestion and Amazon Kinesis Data Analytics for transformation provides a fully managed, serverless architecture that easily handles sliding window calculations with minimal operational overhead. Options involving Amazon MSK require managing Kafka clusters, which increases operational complexity. Option B introduces unnecessary architectural components and latency by saving data to S3 and using AWS Lambda, rather than processing the stream directly.