MLA-C01 · Question #12
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 C. Use Amazon SageMaker Data Wrangler to transform the categorical data into numerical data.. Option C is correct because ML algorithms require numerical inputs, so categorical features (e.g., transaction type, merchant category) must be encoded as numbers - and SageMaker Data Wrangler is a purpose-built, low-code/no-code data preparation tool that natively handles this t
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. The training dataset includes categorical data and numerical data. The ML engineer must prepare the training dataset to maximize the accuracy of the model. Which action will meet this requirement with the LEAST operational overhead?
Options
- AUse AWS Glue to transform the categorical data into numerical data.
- BUse AWS Glue to transform the numerical data into categorical data.
- CUse Amazon SageMaker Data Wrangler to transform the categorical data into numerical data.
- DUse Amazon SageMaker Data Wrangler to transform the numerical data into categorical data.
How the community answered
(41 responses)- A2% (1)
- B17% (7)
- C73% (30)
- D7% (3)
Explanation
Option C is correct because ML algorithms require numerical inputs, so categorical features (e.g., transaction type, merchant category) must be encoded as numbers - and SageMaker Data Wrangler is a purpose-built, low-code/no-code data preparation tool that natively handles this transformation with 300+ built-in recipes, direct S3 connectivity, and seamless SageMaker pipeline integration, all with minimal setup.
Why the distractors fail:
- A - AWS Glue can do categorical-to-numerical transformation, but it requires writing and maintaining ETL scripts, which is significantly higher operational overhead than Data Wrangler's GUI-driven workflow.
- B & D - Both reverse the transformation direction. Converting numerical → categorical would destroy information and make the data less suitable for ML algorithms, which is the opposite of what's needed.
Memory tip: Think "Data Wrangler = drag-and-drop for ML prep." When a question mentions least operational overhead for ML data transformations in SageMaker, Data Wrangler wins over Glue. Also anchor the direction: ML models eat numbers, so the only valid transformation here is categorical → numerical, eliminating B and D immediately.
Topics
Community Discussion
No community discussion yet for this question.