AWS Certified Machine Learning – Specialty — Question 303
A retail company stores 100 GB of daily transactional data in Amazon S3 at periodic intervals. The company wants to identify the schema of the transactional data. The company also wants to perform transformations on the transactional data that is in Amazon S3.
The company wants to use a machine learning (ML) approach to detect fraud in the transformed data.
Which combination of solutions will meet these requirements with the LEAST operational overhead? (Choose three.)
Answer options
- A. Use Amazon Athena to scan the data and identify the schema.
- B. Use AWS Glue crawlers to scan the data and identify the schema.
- C. Use Amazon Redshift to store procedures to perform data transformations.
- D. Use AWS Glue workflows and AWS Glue jobs to perform data transformations.
- E. Use Amazon Redshift ML to train a model to detect fraud.
- F. Use Amazon Fraud Detector to train a model to detect fraud.
Correct answer: B, D, F
Explanation
AWS Glue crawlers automatically discover schema information from Amazon S3 with minimal setup, making option B superior to Athena, which requires manual DDL definition. AWS Glue jobs and workflows provide a serverless, low-overhead method for transforming S3 data directly without needing to provision a data warehouse like Amazon Redshift, ruling out option C. Finally, Amazon Fraud Detector is a fully managed service specifically designed for fraud detection ML models, offering a lower operational overhead than setting up Amazon Redshift ML, which rules out option E.