A data scientist is preparing a dataset for a medical diagnosis model. The dataset is highly imbalanced, with only 1% positive cases. The data scientist applies SMOTE to balance the dataset, then splits the data into training and test sets. After training, the model shows high performance on the test set, but the data scientist is concerned about data leakage. Which practice should they adopt to avoid data leakage?

Use a larger test set to reduce leakage

Apply SMOTE after splitting the data, only to the training set

Apply SMOTE before splitting the data

Use cross-validation instead of a single split

AWSCertified Machine Learning Engineer - Associate

Domain 1Objective 3

Task 1.3: Ensure Data Integrity and Prepare Data for Modeling MLA-C01 Practice Questions (Page 1)

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 28 practice questions to prepare you well beyond it. (estimate)

28questions here

6free pages

9concepts

28%of the exam

Questions 1–5

1foundation · easy
A team is training an image classification model and wants to increase the diversity of the training data to reduce overfitting and prediction bias. Which technique creates new training examples from existing images?
Select an answer first
2foundation · easy
A data engineer wants to visually explore a dataset, identify data quality issues like missing values and outliers, and create a recipe to clean the data without writing code. Which AWS service is designed for this purpose?
Select an answer first
3foundation · easy
A machine learning team suspects that a dataset collected from a mobile app only includes users who opted into sharing data, potentially excluding a large portion of the user base. Which type of bias is this?
Select an answer first
4application · medium
A data engineer is preparing a dataset for a machine learning model that includes a column with free-text comments from customers. The comments may contain personal information such as names and phone numbers. The engineer wants to protect this sensitive information before the dataset is used for training. Which technique should they apply?
Select an answer first
5expert · hard
A data scientist is preparing a dataset for a medical diagnosis model. The dataset is highly imbalanced, with only 1% positive cases. The data scientist applies SMOTE to balance the dataset, then splits the data into training and test sets. After training, the model shows high performance on the test set, but the data scientist is concerned about data leakage. Which practice should they adopt to avoid data leakage?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back 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 1.3: Ensure Data Integrity and Prepare Data for Modeling MLA-C01 Practice Questions (Page 1)

Questions 1–5

A team is training an image classification model and wants to increase the diversity of the training data to reduce overfitting and prediction bias. Which technique creates new training examples from existing images?

A data engineer wants to visually explore a dataset, identify data quality issues like missing values and outliers, and create a recipe to clean the data without writing code. Which AWS service is designed for this purpose?

A machine learning team suspects that a dataset collected from a mobile app only includes users who opted into sharing data, potentially excluding a large portion of the user base. Which type of bias is this?

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