Free Amazon MLA-C01 Practice Exams - Page 6 of 6

Question #51

A company stores its training datasets on Amazon S3 in the form of tabular data running into millions of rows. The company needs to prepare this data for Machine Learning jobs. The data preparation involves data selection, cleansing, exploration, and visualization using a single visual interface.

Which Amazon SageMaker service is the best fit for this requirement?

A . Amazon SageMaker Feature Store
B . Amazon SageMaker Data Wrangler
C . SageMaker Model Dashboard
D . Amazon SageMaker Clarify

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Correct option:

Amazon SageMaker Data Wrangler:

Amazon SageMaker Data Wrangler reduces the time it takes to aggregate and prepare tabular and image data for ML from weeks to minutes. With SageMaker Data Wrangler, you can simplify the process of data preparation and feature engineering, and complete each step of the data preparation workflow (including data selection, cleansing, exploration, visualization, and processing at scale) from a single visual interface. You can use SQL to select the data that you want from various data sources and import it quickly. Next, you can use the data quality and insights report to automatically verify data quality and detect anomalies, such as duplicate rows and target leakage. SageMaker Data Wrangler contains over 300 built-in data transformations, so you can quickly transform data without writing code.

With the SageMaker Data Wrangler data selection tool, you can quickly access and select your tabular and image data from various popular sources – such as Amazon Simple Storage Service (Amazon S3), Amazon Athena, Amazon Redshift, AWS Lake Formation, Snowflake, and Databricks – and over 50 other third-party sources – such as Salesforce, SAP, Facebook Ads, and Google Analytics. You can also write queries for data sources using SQL and import data directly into SageMaker from various file formats, such as CSV, Parquet, JSON, and database tables.

How Data Wrangler works:

via – https://aws.amazon.com/sagemaker/data-wrangler/

Incorrect options:

SageMaker Model Dashboard – Amazon SageMaker Model Dashboard is a centralized portal, accessible from the SageMaker console, where you can view, search, and explore all of the models in your account. You can track which models are deployed for inference and if they are used in batch transform jobs or hosted on endpoints.

Amazon SageMaker Clarify – SageMaker Clarify helps identify potential bias during data preparation without writing code. You specify input features, such as gender or age, and SageMaker Clarify runs an analysis job to detect potential bias in those features.

Amazon SageMaker Feature Store – Amazon SageMaker Feature Store is a fully managed, purpose-built repository to store, share, and manage features for machine learning (ML) models. Features are inputs to ML models used during training and inference.

Reference: https://aws.amazon.com/sagemaker/data-wrangler/

Question #52

You are a machine learning engineer at a fintech company that has developed several models for various use cases, including fraud detection, credit scoring, and personalized marketing. Each model has different performance and deployment requirements. The fraud detection model requires real-time predictions with low latency and needs to scale quickly based on incoming transaction volumes. The credit scoring model is computationally intensive but can tolerate batch processing with slightly higher latency. The personalized marketing model needs to be triggered by events and doesn’t require constant availability.

Given these varying requirements, which deployment target is the MOST SUITABLE for each model?

A . Deploy the fraud detection model using AWS Lambda for serverless, on-demand execution, deploy the credit scoring model on Amazon EKS for scalable batch processing, and deploy the personalized marketing model on SageMaker endpoints to handle event-driven inference
B . Deploy the fraud detection model using SageMaker endpoints for low-latency, real-time predictions, deploy the credit scoring model on Amazon ECS for batch processing, and deploy the personalized marketing model using AWS Lambda for event-driven execution
C . Deploy all three models on a single Amazon EKS cluster to take advantage of Kubernetes orchestration, ensuring consistent management and scaling across different use cases
D . Deploy the fraud detection model on Amazon ECS for auto-scaling based on demand, deploy the credit scoring model using SageMaker endpoints for real-time scoring, and deploy the personalized marketing model on Amazon EKS for event-driven processing

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Correct option:

Deploy the fraud detection model using SageMaker endpoints for low-latency, real-time predictions, deploy the credit scoring model on Amazon ECS for batch processing, and deploy the personalized marketing model using AWS Lambda for event-driven execution

Real-time inference is ideal for inference workloads where you have real-time, interactive, low latency requirements. You can deploy your model to SageMaker hosting services and get an endpoint that can be used for inference. These endpoints are fully managed and support autoscaling. SageMaker endpoints are optimized for low-latency, real-time predictions, making them ideal for the fraud detection model.

Amazon ECS provides a service scheduler for long-running tasks and applications. It also provides the ability to run standalone tasks or scheduled tasks for batch jobs or single run tasks. You can specify the task placement strategies and constraints for running tasks that best meet your needs. Amazon ECS is well-suited for batch processing tasks, making it a good choice for the credit scoring model.

AWS Lambda is ideal for the event-driven nature of the personalized marketing model, allowing it to scale on-demand with minimal cost.

via – https://docs.aws.amazon.com/AmazonECS/latest/developerguide/scheduling_tasks.html

Incorrect options:

Deploy the fraud detection model using AWS Lambda for serverless, on-demand execution, deploy the credit scoring model on Amazon EKS for scalable batch processing, and deploy the personalized marketing model on SageMaker endpoints to handle event-driven inference – AWS Lambda is serverless and ideal for event-driven tasks, but it may not provide the low-latency, real-time performance required for fraud detection. SageMaker endpoints are better suited for this use case. The credit scoring model is better suited for ECS, where batch processing can be efficiently managed, while personalized marketing is a good fit for AWS Lambda.

Deploy all three models on a single Amazon EKS cluster to take advantage of Kubernetes orchestration, ensuring consistent management and scaling across different use cases – Deploying all models on a

single Amazon EKS cluster could be overkill and lead to unnecessary complexity. While Kubernetes provides powerful orchestration, it might be excessive for simple, event-driven or batch workloads.

Deploy the fraud detection model on Amazon ECS for auto-scaling based on demand, deploy the credit scoring model using SageMaker endpoints for real-time scoring, and deploy the personalized marketing model on Amazon EKS for event-driven processing – While Amazon ECS can handle auto-scaling, it is not as optimized for real-time, low-latency predictions as SageMaker endpoints. Additionally, using SageMaker endpoints for the credit scoring model does not align well with batch processing needs. The personalized marketing model is better suited to AWS Lambda rather than Amazon EKS, which is more complex and designed for containerized applications with continuous workloads.

References:

https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html

https://docs.aws.amazon.com/AmazonECS/latest/developerguide/scheduling_tasks.html

Question #53

You are a machine learning engineer responsible for managing a fraud detection model deployed on Amazon SageMaker. The model needs to be retrained periodically as new transaction data becomes available and as data distribution shifts over time. To ensure compliance and traceability, the company requires that all re-training activities, including data access and model updates, be logged and monitored. Additionally, the security team wants to be notified of any unauthorized attempts to retrain the model.

How can you use AWS CloudTrail to meet these guidelines?

A . Enable detailed monitoring in Amazon CloudWatch to track all SageMaker activities, and use CloudWatch Logs to store and analyze the logs for any suspicious activity related to re-training
B . Enable AWS CloudTrail to log all API calls related to SageMaker, including CreateTrainingJob and UpdateEndpoint, and configure CloudWatch Alarms to notify the security team if unauthorized API calls are detected
C . Configure AWS CloudTrail to log only the data access events that trigger re-training, and manually trigger model re-training when changes in the data are detected through these logs
D . Enable AWS CloudWatch to log all API calls related to SageMaker, including CreateTrainingJob and UpdateEndpoint, and configure CloudWatch Alarms to notify the security team if unauthorized API calls are detected

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Correct option:

Enable AWS CloudTrail to log all API calls related to SageMaker, including CreateTrainingJob and UpdateEndpoint, and configure CloudWatch Alarms to notify the security team if unauthorized API calls are detected

This option leverages AWS CloudTrail to log all relevant API activities related to SageMaker, providing full traceability of re-training events and any updates to the model. By configuring CloudWatch Alarms, you can automatically notify the security team if any suspicious or unauthorized actions are detected. This approach meets both compliance and operational requirements.

via – https://docs.aws.amazon.com/awscloudtrail/latest/userguide/cloudtrail-user-guide.html

Incorrect options:

Configure AWS CloudTrail to log only the data access events that trigger re-training, and manually trigger model re-training when changes in the data are detected through these logs – Monitoring only data access events in S3 is insufficient because it misses other critical re-training activities, such as creating training jobs or updating endpoints. Manual log reviews are prone to errors and delay in detecting unauthorized activities.

Enable detailed monitoring in Amazon CloudWatch to track all SageMaker activities, and use CloudWatch Logs to store and analyze the logs for any suspicious activity related to re-training – While CloudWatch is useful for performance monitoring, CloudTrail is specifically designed to log and monitor API activity across AWS services, making it more appropriate for tracking re-training activities and ensuring compliance.

Enable AWS CloudWatch to log all API calls related to SageMaker, including CreateTrainingJob and UpdateEndpoint, and configure CloudWatch Alarms to notify the security team if unauthorized API calls are detected – You can only use CloudTrail to log and monitor API activity across AWS services. CloudWatch is useful for performance monitoring. So, this option acts as a distractor.

References:

https://docs.aws.amazon.com/awscloudtrail/latest/userguide/cloudtrail-user-guide.html

https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/AlarmThatSendsEmail.html

Question #54

Your company is starting a new machine learning project, and the data preparation tasks are being handled by a team of business analysts. These analysts are more comfortable working with visual tools rather than writing code, and they need to combine, transform, and clean large datasets efficiently. The goal is to use a SageMaker tool that allows them to perform these tasks using a visual, point-and-click interface.

Which SageMaker tool(s) would best suit the team’s requirements for preparing and analyzing data without writing code?

A . Prepare data using Amazon EMR in Studio
B . Use Amazon SageMaker Data Wrangler within Amazon SageMaker Canvas
C . Prepare data with SQL in Amazon SageMaker Studio. The SQL extension connections to Amazon Athena for working with datasets
D . Use Amazon SageMaker Data Wrangler within Amazon SageMaker JumpStart

Reveal Solution Hide Solution

Correct Answer: B
B

Explanation:

Correct option:

Use Amazon SageMaker Data Wrangler within Amazon SageMaker Canvas

Use Amazon SageMaker Data Wrangler in Amazon SageMaker Canvas to prepare, featurize and analyze your data. You can integrate a Data Wrangler data preparation flow into your machine learning (ML) workflows to simplify and streamline data pre-processing and feature engineering using little to no coding. You can also add your own Python scripts and transformations to customize workflows.

Data Flow C Create a data flow to define a series of ML data prep steps. You can use a flow to combine datasets from different data sources, identify the number and types of transformations you want to apply to datasets, and define a data prep workflow that can be integrated into an ML pipeline.

Transform C Clean and transform your dataset using standard transforms like string, vector, and numeric data formatting tools. Featurize your data using transforms like text and date/time embedding and categorical encoding.

Generate Data Insights C Automatically verify data quality and detect abnormalities in your data with Data Wrangler Data Quality and Insights Report.

Analyze C Analyze features in your dataset at any point in your flow. Data Wrangler includes built-in data visualization tools like scatter plots and histograms, as well as data analysis tools like target leakage analysis and quick modeling to understand feature correlation.

Export C Export your data preparation workflow to a different location.

SageMaker Canvas features for ML lifecycle:

via – https://aws.amazon.com/sagemaker/canvas/

Incorrect options:

Prepare data using Amazon EMR in Studio – The integration between Amazon EMR and Amazon SageMaker Studio provides a scalable environment for large-scale data preparation for machine learning. This option is viable only if users are comfortable writing code.

Use Amazon SageMaker Data Wrangler within Amazon SageMaker JumpStart – Amazon SageMaker JumpStart is a machine learning (ML) hub that can help you accelerate your ML journey. With SageMaker JumpStart, you can evaluate, compare, and select FMs quickly based on pre-defined quality and responsibility metrics to perform tasks like article summarization and image generation. SageMaker JumpStart is not the right tool for the given use case.

Prepare data with SQL in Amazon SageMaker Studio. The SQL extension connections to Amazon Athena for working with datasets – Amazon SageMaker Studio provides a built-in SQL extension. This

extension allows data scientists to perform tasks such as sampling, exploratory analysis, and feature engineering directly within the JupyterLab notebooks. However, this option does not offer any no-code features.

References:

https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-data-prep.html

https://docs.aws.amazon.com/sagemaker/latest/dg/data-prep.html

Question #55

You are a machine learning engineer responsible for maintaining an ML pipeline that processes customer transaction data to detect fraudulent activity. The pipeline includes several stages: data ingestion, data preprocessing, model inference, and result storage. The pipeline runs continuously, processing large volumes of data in near real-time. Recently, you’ve noticed that some transactions are being incorrectly classified as non-fraudulent, raising concerns about potential anomalies or errors in the data processing or model inference stages.

Given the critical nature of the pipeline, which approach is the MOST EFFECTIVE for addressing these issues?

A . Schedule periodic manual reviews of a random sample of processed transactions to check for anomalies or errors, documenting any issues for further investigation
B . Use AWS Lambda functions to log and audit every transaction processed by the pipeline, storing detailed logs in Amazon S3 for manual analysis when anomalies are suspected
C . Implement Amazon SageMaker Model Monitor to track the distribution of input data features and model predictions over time, alerting you when deviations from expected patterns occur
D . Set up Amazon CloudWatch alarms to monitor CPU and memory usage across the pipeline’s compute resources, and trigger notifications if these metrics exceed predefined thresholds

Reveal Solution Hide Solution

Correct Answer: C
C

Explanation:

Correct option:

Implement Amazon SageMaker Model Monitor to track the distribution of input data features and model predictions over time, alerting you when deviations from expected patterns occur

Amazon SageMaker Model Monitor is designed to track the distribution of input data features and monitor model predictions for anomalies. It provides alerts when deviations from expected patterns are detected, making it an effective tool for detecting data drift, concept drift, and other issues that could lead to incorrect classifications.

via – https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor.html

Incorrect options:

Set up Amazon CloudWatch alarms to monitor CPU and memory usage across the pipeline’s compute resources, and trigger notifications if these metrics exceed predefined thresholds – While monitoring CPU and memory usage can help identify performance issues, it does not directly address anomalies or errors in data processing or model inference. These metrics are not sufficient to detect issues like data drift or changes in model behavior.

Schedule periodic manual reviews of a random sample of processed transactions to check for anomalies or errors, documenting any issues for further investigation – Manual reviews can be helpful for spot-checking, but they are not scalable or reliable for continuous monitoring, especially in a high-volume, real-time pipeline. Automated monitoring is more effective for catching issues as they arise.

Use AWS Lambda functions to log and audit every transaction processed by the pipeline, storing detailed logs in Amazon S3 for manual analysis when anomalies are suspected – Logging and auditing every transaction with AWS Lambda functions can provide detailed insights, but it is resource-intensive and does not offer real-time anomaly detection. This approach is better suited for post-mortem analysis rather than proactive monitoring.

Reference: https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor.html

Question #56

A company has recently migrated to AWS Cloud and it wants to optimize the hardware used for its AI workflows.

Which of the following would you suggest?

A . Leverage either AWS Trainium or AWS Inferentia for the deep learning (DL) and generative AI inference applications
B . Leverage AWS Trainium for high-performance, cost-effective Deep Learning training. Leverage AWS Inferentia for the deep learning (DL) and generative AI inference applications
C . Leverage either AWS Trainium or AWS Inferentia for high-performance, cost-effective Deep Learning training
D . Leverage AWS Inferentia for high-performance, cost-effective Deep Learning training. Leverage AWS Trainium for the deep learning (DL) and generative AI inference applications

Reveal Solution Hide Solution

Question #57

You are a data scientist working for an e-commerce company that wants to implement personalized product recommendations for its users. The company has a large dataset of user interactions, including clicks, purchases, and reviews. The goal is to create a recommendation system that can scale to millions of users while providing real-time recommendations based on user behavior. You need to choose the most appropriate built-in algorithm in Amazon SageMaker to achieve this goal.

Given the requirements, which of the following Amazon SageMaker built-in algorithms is the MOST SUITABLE for this use case?

A . XGBoost Algorithm to rank the products based on user behavior and demographic features
B . K-Means Algorithm to cluster users into segments and recommend products based on these segments
C . Factorization Machines Algorithm to model user-item interactions for collaborative filtering
D . BlazingText Algorithm to analyze the text in user reviews and identify product similarities

Reveal Solution Hide Solution

Correct Answer: C
C

Explanation:

Correct option:

Factorization Machines Algorithm to model user-item interactions for collaborative filtering

The Factorization Machines algorithm is a general-purpose supervised learning algorithm that you can use for both classification and regression tasks. It is an extension of a linear model that is designed to capture interactions between features within high dimensional sparse datasets economically. For example, in a click prediction system, the Factorization Machines model can capture click rate patterns observed when ads from a certain ad-category are placed on pages from a certain page-category. Factorization machines are a good choice for tasks dealing with high dimensional sparse datasets, such as click prediction and item recommendation.

Factorization Machines is well-suited for collaborative filtering. It excels at modeling sparse user-item interactions, making it ideal for large-scale recommendation systems where there are many users and items but relatively few interactions for each user-item pair. This algorithm can effectively capture latent factors to provide personalized recommendations.

Mapping use cases to built-in algorithms:

via – https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html

Incorrect options:

XGBoost Algorithm to rank the products based on user behavior and demographic features – XGBoost is a powerful algorithm for ranking and classification tasks, but it’s not optimized for collaborative filtering, which is crucial for personalized recommendations in this context.

BlazingText Algorithm to analyze the text in user reviews and identify product similarities – BlazingText is effective for text classification and word embedding but is not specifically designed for recommendation systems. While it can be used to analyze user reviews, it does not address the core requirement of user-item interaction modeling.

K-Means Algorithm to cluster users into segments and recommend products based on these segments – K-Means is useful for clustering users into segments, but this approach is more generalized and does not provide the level of personalization required for individual recommendations based on specific user-item interactions.

References:

https://docs.aws.amazon.com/sagemaker/latest/dg/fact-machines.html

https://aws.amazon.com/blogs/machine-learning/accelerate-and-improve-recommender-system-training-and-predictions-using-amazon-sagemaker-feature-store/

https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html

Question #58

What is a key difference in feature engineering tasks for structured data compared to unstructured data in the context of machine learning?

A . Feature engineering for structured data is not necessary as the data is already in a usable format, whereas for unstructured data, extensive preprocessing is always required
B . Feature engineering for structured data often involves tasks such as normalization and handling missing values, while for unstructured data, it involves tasks such as tokenization and vectorization
C . Feature engineering tasks for structured data and unstructured data are identical and do not vary based on data type
D . Feature engineering for structured data focuses on image recognition, whereas for unstructured
data, it focuses on numerical data analysis

Reveal Solution Hide Solution