A data engineer is using AWS Glue DataBrew to prepare a dataset for a machine learning model. The dataset contains a 'salary' column with some missing values and a few extreme outliers that are known data entry errors. The engineer needs to clean the data before feature engineering. Which sequence of steps should the engineer perform in DataBrew?

First remove the outlier rows, then impute the missing salary values with the median salary.

First impute the missing values with the mean salary, then remove the outlier rows.

Impute the missing values with zero, and then standardize the salary column.

Remove all rows with missing values, and then cap the outliers at the 95th percentile.

A data scientist is building a model to predict customer lifetime value. The dataset includes a 'total_purchases' column that is heavily right-skewed, with most customers having few purchases and a few having many. The data scientist plans to use a linear regression model. Which feature transformation should the data scientist apply to 'total_purchases'?

Apply a standard scaler to 'total_purchases'.

Apply a label encoding to 'total_purchases' after binning it into categories.

Apply a min-max normalization to 'total_purchases'.

Apply a log transformation to 'total_purchases'.

A data science team is developing a fraud detection model. They have a training pipeline that computes features like 'transaction_amount_7d_avg' and 'user_login_frequency'. They want to ensure that the exact same feature values are used during both model training and real-time inference. The team also wants to share these features across multiple models. Which solution should they implement?

Use AWS Glue DataBrew to create the features and store them in a DynamoDB table for fast access during inference.

Recompute the features in both the training and inference pipelines using the same code to ensure consistency.

Use SageMaker Feature Store to define, store, and share the features, and use the same feature store for both training and inference.

Store the computed features in a central Amazon S3 bucket and have both the training and inference pipelines read from it.

AWSCertified Machine Learning Engineer - Associate

Domain 1Objective 2

Task 1.2: Transform Data and Perform Feature Engineering MLA-C01 Practice Questions (Page 5)

Part of the Content Domain 1: Data Preparation for Machine Learning (ML) domain, which accounts for 28% of the MLA-C01 exam. AWS does not publish an official question count, but from its 130-minute exam (~50–85 total, ~14–24 in this domain), expect 5–8 from this objective — we provide 25 practice questions to prepare you well beyond it. (estimate)

25questions here

5free pages

9concepts

28%of the exam

Questions 21–25

21application · medium
A data engineer is using AWS Glue DataBrew to prepare a dataset for a machine learning model. The dataset contains a 'salary' column with some missing values and a few extreme outliers that are known data entry errors. The engineer needs to clean the data before feature engineering. Which sequence of steps should the engineer perform in DataBrew?
Select an answer first
22application · medium
A data scientist is building a model to predict customer lifetime value. The dataset includes a 'total_purchases' column that is heavily right-skewed, with most customers having few purchases and a few having many. The data scientist plans to use a linear regression model. Which feature transformation should the data scientist apply to 'total_purchases'?
Select an answer first
23foundation · easy
A data scientist wants to visually explore a dataset and create a data transformation flow without writing code, using a fully managed AWS service. Which AWS service is designed for this purpose?
Select an answer first
24application · medium
A data science team is developing a fraud detection model. They have a training pipeline that computes features like 'transaction_amount_7d_avg' and 'user_login_frequency'. They want to ensure that the exact same feature values are used during both model training and real-time inference. The team also wants to share these features across multiple models. Which solution should they implement?
Select an answer first
25foundation · easy
A data engineer needs to run a serverless ETL job that transforms data in an Amazon S3 bucket and loads it into another S3 bucket. Which AWS service is purpose-built for this type of serverless ETL?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to MLA-C01

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by AWS. “MLA-C01” is a trademark of its owner, used for identification only.

Task 1.2: Transform Data and Perform Feature Engineering MLA-C01 Practice Questions (Page 5)

Questions 21–25

A data scientist wants to visually explore a dataset and create a data transformation flow without writing code, using a fully managed AWS service. Which AWS service is designed for this purpose?

A data engineer needs to run a serverless ETL job that transforms data in an Amazon S3 bucket and loads it into another S3 bucket. Which AWS service is purpose-built for this type of serverless ETL?

Keep studying — Content Domain 1: Data Preparation for Machine Learning (ML)