MLS-C01 Question Bank · Latest 50 Questions Free Preview (Page 4/5)

A telecommunications company has deployed a machine learning model using Amazon SageMaker. The model identifies customers who are likely to cancel their contract when calling customer service. These customers are then directed to a specialist service team. The model has been trained on historical data from multiple years relating to customer contracts and customer service interactions in a single geographic region. The company is planning to launch a new global product that will use this model. Management is concerned that the model might incorrectly direct a large number of calls from customers in regions without historical data to the specialist service team. Which approach would MOST effectively address this issue?

• A. Enable Amazon SageMaker Model Monitor data capture on the model endpoint. Create a monitoring baseline on the training dataset. Schedule monitoring jobs. Use Amazon CloudWatch to alert the data scientists when the numerical distance of regional customer data fails the baseline drift check. Reevaluate the training set with the larger data source and retrain the model.
• B. Enable Amazon SageMaker Debugger on the model endpoint. Create a custom rule to measure the variance from the baseline training dataset. Use Amazon CloudWatch to alert the data scientists when the rule is invoked. Reevaluate the training set with the larger data source and retrain the model.
• C. Capture all customer calls routed to the specialist service team in Amazon S3. Schedule a monitoring job to capture all the true positives and true negatives, correlate them to the training dataset, and calculate the accuracy. Use Amazon CloudWatch to alert the data scientists when the accuracy decreases. Reevaluate the training set with the additional data from the specialist service team and retrain the model.
• D. Enable Amazon CloudWatch on the model endpoint. Capture metrics using Amazon CloudWatch Logs and send them to Amazon S3. Analyze the monitored results against the training data baseline. When the variance from the baseline exceeds the regional customer variance, reevaluate the training set and retrain the model.

Answer: A

A car company has dealership locations in multiple cities. The company uses a machine learning (ML) recommendation system to market cars to its customers. An ML engineer trained the ML recommendation model on a dataset that includes multiple attributes about each car. The dataset includes attributes such as car brand, car type, fuel efficiency, and price. The ML engineer uses Amazon SageMaker Data Wrangler to analyze and visualize data. The ML engineer needs to identify the distribution of car prices for a specific type of car. Which type of visualization should the ML engineer use to meet these requirements?

• A. Use the SageMaker Data Wrangler scatter plot visualization to inspect the relationship between the car price and type of car.
• B. Use the SageMaker Data Wrangler quick model visualization to quickly evaluate the data and produce importance scores for the car price and type of car.
• C. Use the SageMaker Data Wrangler anomaly detection visualization to Identify outliers for the specific features.
• D. Use the SageMaker Data Wrangler histogram visualization to inspect the range of values for the specific feature.

Answer: D

A global bank requires a solution to predict whether customers will leave the bank and choose another bank. The bank is using a dataset to train a model to predict customer loss. The training dataset has 1,000 rows. The training dataset includes 100 instances of customers who left the bank. A machine learning (ML) specialist is using Amazon SageMaker Data Wrangler to train a churn prediction model by using a SageMaker training job. After training, the ML specialist notices that the model returns only false results. The ML specialist must correct the model so that it returns more accurate predictions. Which solution will meet these requirements?

• A. Apply anomaly detection to remove outliers from the training dataset before training.
• B. Apply Synthetic Minority Oversampling Technique (SMOTE) to the training dataset before training.
• C. Apply normalization to the features of the training dataset before training.
• D. Apply undersampling to the training dataset before training.

Answer: B

A media company wants to deploy a machine learning (ML) model that uses Amazon SageMaker to recommend new articles to the company’s readers. The company's readers are primarily located in a single city. The company notices that the heaviest reader traffic predictably occurs early in the morning, after lunch, and again after work hours. There is very little traffic at other times of day. The media company needs to minimize the time required to deliver recommendations to its readers. The expected amount of data that the API call will return for inference is less than 4 MB. Which solution will meet these requirements in the MOST cost-effective way?

• A. Real-time inference with auto scaling
• B. Serverless inference with provisioned concurrency
• C. Asynchronous inference
• D. A batch transform task

Answer: B

A bank has collected customer data for 10 years in CSV format. The bank stores the data in an on-premises server. A data science team wants to use Amazon SageMaker to build and train a machine learning (ML) model to predict churn probability. The team will use the historical data. The data scientists want to perform data transformations quickly and to generate data insights before the team builds a model for production. Which solution will meet these requirements with the LEAST development effort?

• A. Upload the data into the SageMaker Data Wrangler console directly. Perform data transformations and generate insights within Data Wrangler.
• B. Upload the data into an Amazon S3 bucket. Allow SageMaker to access the data that is in the bucket. Import the data from the S3 bucket into SageMaker Data Wrangler. Perform data transformations and generate insights within Data Wrangler.
• C. Upload the data into the SageMaker Data Wrangler console directly. Allow SageMaker and Amazon QuickSight to access the data that is in an Amazon S3 bucket. Perform data transformations in Data Wrangler and save the transformed data into a second S3 bucket. Use QuickSight to generate data insights.
• D. Upload the data into an Amazon S3 bucket. Allow SageMaker to access the data that is in the bucket. Import the data from the bucket into SageMaker Data Wrangler. Perform data transformations in Data Wrangler. Save the data into a second S3 bucket. Use a SageMaker Studio notebook to generate data insights.

Answer: B

An agriculture company wants to improve crop yield forecasting for the upcoming season by using crop yields from the last three seasons. The company wants to compare the performance of its new scikit-learn model to the benchmark. A data scientist needs to package the code into a container that computes both the new model forecast and the benchmark. The data scientist wants AWS to be responsible for the operational maintenance of the container. Which solution will meet these requirements?

• A. Package the code as the training script for an Amazon SageMaker scikit-learn container.
• B. Package the code into a custom-built container. Push the container to Amazon Elastic Container Registry (Amazon ECR).
• C. Package the code into a custom-built container. Push the container to AWS Fargate.
• D. Package the code by extending an Amazon SageMaker scikit-learn container.

Answer: D

A cybersecurity company is collecting on-premises server logs, mobile app logs, and IoT sensor data. The company backs up the ingested data in an Amazon S3 bucket and sends the ingested data to Amazon OpenSearch Service for further analysis. Currently, the company has a custom ingestion pipeline that is running on Amazon EC2 instances. The company needs to implement a new serverless ingestion pipeline that can automatically scale to handle sudden changes in the data flow. Which solution will meet these requirements MOST cost-effectively?

• A. Create two Amazon Data Firehose delivery streams to send data to the S3 bucket and OpenSearch Service. Configure the data sources to send data to the delivery streams.
• B. Create one Amazon Kinesis data stream. Create two Amazon Data Firehose delivery streams to send data to the S3 bucket and OpenSearch Service. Connect the delivery streams to the data stream. Configure the data sources to send data to the data stream.
• C. Create one Amazon Data Firehose delivery stream to send data to OpenSearch Service. Configure the delivery stream to back up the raw data to the S3 bucket. Configure the data sources to send data to the delivery stream.
• D. Create one Amazon Kinesis data stream. Create one Amazon Data Firehose delivery stream to send data to OpenSearch Service. Configure the delivery stream to back up the data to the S3 bucket. Connect the delivery stream to the data stream. Configure the data sources to send data to the data stream.

Answer: C

A business to business (B2B) ecommerce company wants to develop a fair and equitable risk mitigation strategy to reject potentially fraudulent transactions. The company wants to reject fraudulent transactions despite the possibility of losing some profitable transactions or customers. Which solution will meet these requirements with the LEAST operational effort?

• A. Use Amazon SageMaker to approve transactions only for products the company has sold in the past.
• B. Use Amazon SageMaker to train a custom fraud detection model based on customer data.
• C. Use the Amazon Fraud Detector prediction API to approve or deny any activities that Fraud Detector identifies as fraudulent.
• D. Use the Amazon Fraud Detector prediction API to identify potentially fraudulent activities so the company can review the activities and reject fraudulent transactions.

Answer: C

A manufacturing company produces 100 types of steel rods. The rod types have varying material grades and dimensions. The company has sales data for the steel rods for the past 50 years. A data scientist needs to build a machine learning (ML) model to predict future sales of the steel rods. Which solution will meet this requirement in the MOST operationally efficient way?

• A. Use the Amazon SageMaker DeepAR forecasting algorithm to build a single model for all the products.
• B. Use the Amazon SageMaker DeepAR forecasting algorithm to build separate models for each product.
• C. Use Amazon SageMaker Autopilot to build a single model for all the products.
• D. Use Amazon SageMaker Autopilot to build separate models for each product.

Answer: A

A machine learning (ML) specialist is building a credit score model for a financial institution. The ML specialist has collected data for the previous 3 years of transactions and third-party metadata that is related to the transactions. After the ML specialist builds the initial model, the ML specialist discovers that the model has low accuracy for both the training data and the test data. The ML specialist needs to improve the accuracy of the model. Which solutions will meet this requirement? (Choose two.)

• A. Increase the number of passes on the existing training data. Perform more hyperparameter tuning.
• B. Increase the amount of regularization. Use fewer feature combinations.
• C. Add new domain-specific features. Use more complex models.
• D. Use fewer feature combinations. Decrease the number of numeric attribute bins.
• E. Decrease the amount of training data examples. Reduce the number of passes on the existing training data.

Answer: A, C