A financial institution is building a model to approve or deny loan applications. Regulatory requirements mandate that the institution must be able to explain each decision to customers. The data is tabular with a mix of numeric and categorical features. Which modeling approach best balances accuracy and interpretability?

Use a deep neural network with a large number of hidden layers to maximize accuracy.

Use a k-nearest neighbors model and rely on the nearest neighbors to explain decisions.

Use a linear regression model to predict the loan amount, not approval.

Use a gradient-boosted tree model and apply SHAP to generate feature importance explanations.

A data science team needs to build a model to detect fraudulent credit card transactions. The dataset has millions of transactions with features like amount, merchant category, and time. The team wants to use a SageMaker built-in algorithm that is optimized for binary classification on tabular data. Which algorithm should they choose?

Latent Dirichlet Allocation (LDA)

A manufacturing company wants to predict equipment failure before it happens using sensor data. They have only 200 labeled failure events out of millions of normal operations. The data is highly imbalanced. The company wants to minimize false negatives (missed failures). Which approach is most appropriate?

Use a deep neural network with a large number of layers to capture complex patterns.

Use a clustering algorithm to identify anomalies in the sensor data.

Use a linear regression model to predict the time until failure.

Use a gradient-boosted tree model with class weights to handle imbalance and tune the decision threshold.

A media company receives thousands of customer support tickets daily in multiple languages. They want to automatically categorize tickets by issue type and route them to the appropriate team. The solution must handle text in English, Spanish, and French. Which AWS service combination should be used?

Use Amazon Textract to extract text from tickets, then use Amazon Polly to generate category labels.

Use Amazon Transcribe to convert audio tickets to text, then use Amazon Rekognition to categorize the text.

Use Amazon SageMaker to train a custom deep learning model from scratch on the ticket data.

Use Amazon Comprehend for language detection and custom classification, and Amazon Translate to translate non-English tickets to English before classification.

AWSCertified Machine Learning Engineer - Associate

Domain 2Objective 1

Task 2.1: Choose a Modeling Approach MLA-C01 Practice Questions (Page 1)

Part of the Content Domain 2: ML Model Development domain, which accounts for 26% of the MLA-C01 exam. AWS does not publish an official question count, but from its 130-minute exam (~50–85 total, ~13–22 in this domain), expect 4–7 from this objective — we provide 32 practice questions to prepare you well beyond it. (estimate)

32questions here

7free pages

9concepts

26%of the exam

Questions 1–5

1application · medium
A financial institution is building a model to approve or deny loan applications. Regulatory requirements mandate that the institution must be able to explain each decision to customers. The data is tabular with a mix of numeric and categorical features. Which modeling approach best balances accuracy and interpretability?
Select an answer first
2application · easy
A data science team needs to build a model to detect fraudulent credit card transactions. The dataset has millions of transactions with features like amount, merchant category, and time. The team wants to use a SageMaker built-in algorithm that is optimized for binary classification on tabular data. Which algorithm should they choose?
Select an answer first
3expert · hard
A manufacturing company wants to predict equipment failure before it happens using sensor data. They have only 200 labeled failure events out of millions of normal operations. The data is highly imbalanced. The company wants to minimize false negatives (missed failures). Which approach is most appropriate?
Select an answer first
4foundation · easy
A company needs to deploy a model for real-time inference. They are comparing a large deep learning model and a smaller gradient boosting model. Both achieve similar accuracy on the validation set. Which factor should be the primary consideration when choosing between them from a cost perspective?
Select an answer first
5application · medium
A media company receives thousands of customer support tickets daily in multiple languages. They want to automatically categorize tickets by issue type and route them to the appropriate team. The solution must handle text in English, Spanish, and French. Which AWS service combination 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 2.1: Choose a Modeling Approach MLA-C01 Practice Questions (Page 1)

Questions 1–5

A company needs to deploy a model for real-time inference. They are comparing a large deep learning model and a smaller gradient boosting model. Both achieve similar accuracy on the validation set. Which factor should be the primary consideration when choosing between them from a cost perspective?

Keep studying — Content Domain 2: ML Model Development