AWS Certified AI PractitionerAWS Services for AI/ML and Generative AIMedium
A data analytics team is building a pipeline to process real-time financial market data. They need to analyze streaming data to detect sudden price changes or trading anomalies using machine learning models. The solution must be able to handle high throughput data streams, invoke custom ML inference endpoints, and scale automatically to accommodate fluctuating data volumes. Which AWS service is best suited to orchestrate the real-time processing and ML inference?
- AAmazon Redshift
- BAmazon Kinesis Data Analytics
- CAWS Batch
- DAmazon S3
Show answer & explanationAnswer & explanation
Correct answer: B. Amazon Kinesis Data Analytics
Amazon Kinesis Data Analytics allows for real-time processing of streaming data using SQL or Apache Flink. It can be configured to invoke external ML inference endpoints (e.g., SageMaker endpoints) for real-time anomaly detection and scales automatically, perfectly matching the requirements for high-throughput streaming data analysis and ML inference.
Why the other options are wrong
- A. Amazon Redshift is a data warehouse for analytical queries on structured data, not for real-time stream processing.
- C. AWS Batch is for running batch computing workloads, not real-time stream processing.
- D. Amazon S3 is object storage and is not designed for real-time streaming data processing or ML inference.
Amazon Kinesis Data Analytics
A fully managed service that allows you to easily analyze streaming data in real time with Apache Flink or SQL.
- Processes data from Kinesis Data Streams or Kinesis Data Firehose.
- Supports real-time anomaly detection and aggregations.
- Can invoke external endpoints for ML inference.
Memory trick: Kinesis Analytics streams ML insights.