A machine learning team is building a model to predict customer default. The dataset contains a feature 'gender' and the target 'default'. The team suspects that the model may be biased against a particular gender. They run SageMaker Clarify and find that the difference in proportions of labels (DPL) is 0.2, which exceeds their threshold of 0.1. The team wants to reduce this bias while maintaining model performance. Which approach should they take?

Remove the 'gender' feature from the dataset

Use a pre-training bias mitigation technique, such as reweighting the samples

Apply a post-training bias mitigation technique, such as threshold adjustment

Use a combination of data balancing, feature engineering, and post-training calibration

A machine learning team is training a model on a large dataset that is stored in Amazon S3. The training job runs on multiple instances and needs to access the data with low latency and high throughput. The team is considering using Amazon EFS or Amazon FSx for Lustre. Which factor should they consider when choosing between the two?

EFS provides higher throughput than FSx for Lustre for large datasets

FSx for Lustre can be linked directly to S3 for data loading

FSx for Lustre is more cost-effective for small datasets

EFS is a POSIX file system, while FSx for Lustre is not

A machine learning pipeline transfers a training dataset from an Amazon S3 bucket to an Amazon SageMaker training instance. To protect the data while it is being transferred, which mechanism should be used?

S3 Server-Side Encryption (SSE)

TLS/SSL encryption for the data in transit

AWS Key Management Service (KMS) key rotation

AWSCertified Machine Learning Engineer - Associate

Domain 1Objective 3

Task 1.3: Ensure Data Integrity and Prepare Data for Modeling MLA-C01 Practice Questions (Page 4)

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 16–20

16foundation · easy
A company operates in the European Union and must ensure that personal data of EU citizens is stored in a specific geographic location to comply with data protection regulations. Which compliance requirement is this addressing?
Select an answer first
17expert · hard
A machine learning team is building a model to predict customer default. The dataset contains a feature 'gender' and the target 'default'. The team suspects that the model may be biased against a particular gender. They run SageMaker Clarify and find that the difference in proportions of labels (DPL) is 0.2, which exceeds their threshold of 0.1. The team wants to reduce this bias while maintaining model performance. Which approach should they take?
Select an answer first
18foundation · easy
A team needs to define automated rules to check for data quality issues, such as null values and value ranges, in a dataset stored in an S3 bucket. Which AWS service allows them to define and run these data quality rules?
Select an answer first
19expert · hard
A machine learning team is training a model on a large dataset that is stored in Amazon S3. The training job runs on multiple instances and needs to access the data with low latency and high throughput. The team is considering using Amazon EFS or Amazon FSx for Lustre. Which factor should they consider when choosing between the two?
Select an answer first
20foundation · easy
A machine learning pipeline transfers a training dataset from an Amazon S3 bucket to an Amazon SageMaker training instance. To protect the data while it is being transferred, which mechanism should be used?
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 4)

Questions 16–20

A company operates in the European Union and must ensure that personal data of EU citizens is stored in a specific geographic location to comply with data protection regulations. Which compliance requirement is this addressing?

A team needs to define automated rules to check for data quality issues, such as null values and value ranges, in a dataset stored in an S3 bucket. Which AWS service allows them to define and run these data quality rules?

A machine learning pipeline transfers a training dataset from an Amazon S3 bucket to an Amazon SageMaker training instance. To protect the data while it is being transferred, which mechanism should be used?

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