MLA-C01 · Question #13
Case Study An ML engineer is developing a fraud detection model on AWS. The training dataset includes transaction logs, customer profiles, and tables from an on-premises MySQL database. The transactio
The correct answer is D. Use the Amazon SageMaker Data Wrangler balance data operation to oversample the minority. Option D is correct because Amazon SageMaker Data Wrangler provides a built-in "balance data" operation that directly handles class imbalance through oversampling with minimal setup - no custom code, no separate service orchestration, and it integrates seamlessly into the SageMak
Question
Case Study An ML engineer is developing a fraud detection model on AWS. The training dataset includes transaction logs, customer profiles, and tables from an on-premises MySQL database. The transaction logs and customer profiles are stored in Amazon S3. The dataset has a class imbalance that affects the learning of the model's algorithm. Additionally, many of the features have interdependencies. The algorithm is not capturing all the desired underlying patterns in the data. Before the ML engineer trains the model, the ML engineer must resolve the issue of the imbalanced data. Which solution will meet this requirement with the LEAST operational effort?
Options
- AUse Amazon Athena to identify patterns that contribute to the imbalance. Adjust the dataset
- BUse Amazon SageMaker Studio Classic built-in algorithms to process the imbalanced dataset.
- CUse AWS Glue DataBrew built-in features to oversample the minority class.
- DUse the Amazon SageMaker Data Wrangler balance data operation to oversample the minority
How the community answered
(31 responses)- A3% (1)
- B10% (3)
- C3% (1)
- D84% (26)
Explanation
Option D is correct because Amazon SageMaker Data Wrangler provides a built-in "balance data" operation that directly handles class imbalance through oversampling with minimal setup - no custom code, no separate service orchestration, and it integrates seamlessly into the SageMaker ML workflow already implied by the scenario.
Why the distractors fail:
- A (Athena): Athena is a query/analytics tool for identifying patterns, not a data transformation tool for fixing imbalance - it would require significant manual follow-up work after analysis.
- B (SageMaker built-in algorithms): SageMaker's built-in algorithms handle training, not preprocessing; they don't automatically resolve class imbalance in the dataset before training begins.
- C (Glue DataBrew): DataBrew can do oversampling, but it's a standalone ETL service that requires additional configuration, job setup, and integration steps, making it higher operational effort than Data Wrangler.
Memory tip: Think of SageMaker Data Wrangler as the "one-stop shop" for data prep within the SageMaker ecosystem - whenever an exam question asks for imbalance handling with least effort in an AWS ML pipeline, Data Wrangler's built-in balance operation is almost always the answer because it requires no external services or custom code.
Topics
Community Discussion
No community discussion yet for this question.