Amazon Web ServicesAssociate levelMLA-C01Page 3 of 5

MLA-C01 exam dumps: questions 201 to 300 of 457

Page 3 of the free MLA-C01 question bank for the AWS Certified Machine Learning Engineer - Associate exam. Questions 201 to 300 are listed below, the first 5 in full with answers and explanations. Back to page 1 for the exam overview and FAQ.

Question bank last updated December 2024

Start timed practice exam Questions 201 to 300

Free MLA-C01 practice questions

Questions 201 to 205 of 457

Pick an answer before you open the explanation. Each question also has its own page with a permalink.

MLA-C01 Question 201

Select 3

You are building a binary classification model to predict whether customers will churn. After training the model, you evaluate its performance using an imbalanced dataset where only 5% of customers have churned. While reviewing the metrics, you notice that the model achieves a high accuracy of 96%. However, the recall for the 'churn' class is very low. Which of the following actions would help you better analyze and improve the model's performance?

A
Use precision and recall metrics instead of accuracy to evaluate the model.
B
Generate a confusion matrix to get detailed insights into the classification results.
C
Use a different dataset with a higher percentage of churn cases to evaluate the model.
D
Apply SMOTE (Synthetic Minority Oversampling Technique) to balance the dataset before training.
E
Increase the depth of the decision tree used in the model to improve recall.

Show answer and explanation

Correct answers: A, B, D

Explanation

To analyze model performance on imbalanced datasets, it is crucial to use metrics like precision and recall instead of accuracy, as accuracy can be misleading. Generating a confusion matrix helps in understanding the detailed results for each class. Additionally, rebalancing the dataset using techniques like SMOTE can improve the model's ability to identify minority class instances. These steps collectively help in diagnosing and addressing performance issues.

A. Correct.
Correct. Precision and recall are better suited for analyzing performance on imbalanced datasets, as they provide insights into how well the model identifies the minority class (e.g., churn). Accuracy is not a reliable metric in this scenario.
B. Correct.
Correct. A confusion matrix allows you to understand the distribution of true positives, false positives, true negatives, and false negatives, which is critical for analyzing performance, especially for the 'churn' class.
C. Incorrect.
Incorrect. While using a different dataset with more churn cases might help during training, it does not directly help with analyzing the current model's performance. Instead, rebalancing the data or using better metrics is more appropriate.
D. Correct.
Correct. SMOTE can be used to balance the dataset by oversampling the minority class (churn cases), which can improve the model's performance and recall for the minority class.
E. Incorrect.
Incorrect. Simply increasing the depth of a decision tree does not guarantee better recall for the minority class and might lead to overfitting. The issue is primarily related to class imbalance, not the model's complexity.

MLA-C01 Question 202

Select 3

You have trained a binary classification model using Amazon SageMaker. After evaluating the model's performance, you observe the following metrics on the validation dataset: Accuracy = 0.92, Precision = 0.95, Recall = 0.60. Which of the following actions would help improve the model's performance for a use case where minimizing false negatives is critical?

A
Increase the threshold for classifying a positive prediction.
B
Decrease the threshold for classifying a positive prediction.
C
Collect and include more samples of the minority class in the training dataset.
D
Use a different evaluation metric, such as F1-score, to guide model improvements.
E
Focus on improving the precision further, as it is currently lower than the accuracy.

Show answer and explanation

Correct answers: B, C, D

Explanation

In scenarios where minimizing false negatives is critical, recall is the most important metric to focus on. Decreasing the threshold for positive predictions increases recall, as more positive cases are identified. Incorporating more samples of the minority class helps the model better understand and predict positive cases. Additionally, using a balanced metric like F1-score ensures that recall is adequately prioritized while maintaining reasonable precision.

A. Incorrect.
Increasing the threshold for classifying a positive prediction would likely decrease recall further, as fewer positive predictions would be made, which is counterproductive when minimizing false negatives is critical.
B. Correct.
Decreasing the threshold for classifying a positive prediction would increase recall by capturing more true positives, helping to minimize false negatives.
C. Correct.
Collecting and including more samples of the minority class would help the model learn to better identify positive cases, thereby improving recall and reducing false negatives.
D. Correct.
Using a different evaluation metric, such as F1-score, which balances precision and recall, could help guide model improvements to ensure that recall is not overlooked.
E. Incorrect.
Focusing on improving precision further would not directly address the issue of high false negatives, as precision is already high and recall is the more relevant metric for this scenario.

MLA-C01 Question 203

Single answer

You are training a classification model using Amazon SageMaker, and after the initial evaluation, the model has an F1 score of 0.65. Your business requirement specifies a high precision model because false positives can lead to customer dissatisfaction. Which approach would most effectively improve model performance for this requirement?

A
Adjust the classification threshold to favor higher precision.
B
Increase the size of the training dataset by adding more labeled data.
C
Focus on improving recall by tuning the model hyperparameters.
D
Switch to a different model architecture that is optimized for recall.

Show answer and explanation

Correct answer: A

Explanation

The business requirement emphasizes high precision to minimize false positives. Adjusting the classification threshold is a targeted approach to prioritize precision over recall. Other options, while potentially improving overall model performance, do not specifically address the precision requirement.

A. Correct.
Correct. Adjusting the classification threshold can directly impact precision and recall trade-offs. By increasing the threshold, you can reduce false positives, improving precision at the expense of recall.
B. Incorrect.
Incorrect. Increasing the dataset size may improve both precision and recall, but it does not directly address the need for higher precision in the short term.
C. Incorrect.
Incorrect. Improving recall would likely increase the number of false positives, which contradicts the business requirement for high precision.
D. Incorrect.
Incorrect. Switching to a model optimized for recall does not align with the business requirement to prioritize precision.

MLA-C01 Question 204

Single answer

You are developing a machine learning pipeline on AWS to predict customer churn. Your data is stored in Amazon S3, and the pipeline involves preprocessing, model training, and deployment. You need a service that allows you to easily orchestrate and automate the pipeline steps while integrating seamlessly with other AWS services like SageMaker for training and S3 for data storage. Which AWS service is the most appropriate for this task?

A
AWS Step Functions
B
AWS Glue
C
Amazon SageMaker Pipelines
D
Amazon EMR

Show answer and explanation

Correct answer: C

Explanation

Amazon SageMaker Pipelines is the most appropriate service for this use case because it is specifically designed for orchestrating machine learning workflows on AWS. It provides built-in features for pipeline automation, model training, and deployment, and integrates seamlessly with other AWS services such as SageMaker and S3. While other services like Step Functions and Glue have their own strengths, they do not offer the specialized ML workflow management capabilities of SageMaker Pipelines.

A. Incorrect.
AWS Step Functions is a workflow orchestration service, but it is not purpose-built for machine learning workflows. It can be used for ML tasks, but Amazon SageMaker Pipelines is more suitable for this specific use case.
B. Incorrect.
AWS Glue is primarily used for data integration and ETL (Extract, Transform, Load) purposes. While it can preprocess data, it is not designed to orchestrate end-to-end machine learning pipelines.
C. Correct.
Amazon SageMaker Pipelines is specifically designed for building, automating, and managing end-to-end machine learning workflows. It integrates seamlessly with SageMaker for training, S3 for data storage, and other AWS services, making it the best choice for this scenario.
D. Incorrect.
Amazon EMR is a big data processing service used for distributed data processing with frameworks like Hadoop and Spark. It is not the ideal choice for orchestrating an ML pipeline.

MLA-C01 Question 205

Select 2

A company is building a machine learning pipeline to predict customer churn using Amazon SageMaker. They need to streamline the process of feature engineering, model training, and hyperparameter optimization. Additionally, they want to ensure that the pipeline can be triggered automatically when new customer data is uploaded to an S3 bucket. Which combination of AWS services is best suited for this task?

A
Amazon SageMaker Processing
B
Amazon SageMaker Pipelines
C
AWS Lambda
D
Amazon SageMaker Autopilot
E
AWS Glue

Show answer and explanation

Correct answers: B, C

Explanation

Amazon SageMaker Pipelines provides a managed solution for building, automating, and managing end-to-end machine learning workflows. Combined with AWS Lambda, which can trigger these workflows based on S3 events, these services address the requirement for both automation and event-driven execution.

A. Incorrect.
Amazon SageMaker Processing is useful for preprocessing and feature engineering, but it does not provide orchestration of the entire pipeline or event-driven triggers.
B. Correct.
Amazon SageMaker Pipelines is specifically designed to orchestrate and automate machine learning workflows, making it essential for this task.
C. Correct.
AWS Lambda is ideal for event-driven processing and can trigger the pipeline when new data is uploaded to the S3 bucket.
D. Incorrect.
Amazon SageMaker Autopilot simplifies model training and tuning but does not provide end-to-end pipeline orchestration or event-driven triggers.
E. Incorrect.
AWS Glue is a data integration service that can be used for ETL tasks but is not directly relevant to orchestrating and automating machine learning pipelines.

Timed practice exam

Take a MLA-C01 practice test under exam conditions

65 questions in 130 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam

MLA-C01 practice questions 201 to 300 of 457

Every question has a page with the answer and explanation. Numbers are stable, so you can bookmark or share them. The bank is split into 5 pages of up to 100 questions.