MLA-C01 Question 35
Select 3You are building a machine learning pipeline to process real-time clickstream data from a website. The data needs to be ingested, processed in real-time for feature extraction, and stored for downstream model training. Which AWS services could you use to implement this solution?
- A
Amazon Kinesis Data Streams for ingesting the clickstream data
- B
Amazon S3 for processing the clickstream data in real-time
- C
Amazon Kinesis Data Analytics or Apache Flink for feature extraction in real-time
- D
Amazon S3 for storing the processed data for model training
- E
AWS Glue for real-time feature extraction
Show answer and explanation
Correct answers: A, C, D
Explanation
To build a real-time ML pipeline, you need to first ingest the data using a streaming service like Amazon Kinesis Data Streams. For real-time processing and feature extraction, you can use Amazon Kinesis Data Analytics or Apache Flink. Finally, Amazon S3 is a suitable choice for storing the processed data for later use in model training. AWS Glue is not suitable for real-time processing, and Amazon S3 does not perform processing itself.
- A. Correct.
Correct. Amazon Kinesis Data Streams is designed for ingesting real-time streaming data, such as clickstream data.
- B. Incorrect.
Incorrect. Amazon S3 is a storage service and does not support real-time processing.
- C. Correct.
Correct. Amazon Kinesis Data Analytics or Apache Flink can process streaming data in real-time for use cases such as feature extraction.
- D. Correct.
Correct. Amazon S3 is commonly used for storing processed data, making it accessible for downstream batch processing like model training.
- E. Incorrect.
Incorrect. AWS Glue is an ETL service primarily used for batch processing, not real-time feature extraction.