MLS-C01 practice questions 151–160

1. Question 151 · 368 in bank

   A company is training machine learning (ML) models on Amazon SageMaker by using 200 TB of data that is stored in Amazon S3 buckets. The training data consists of individual files that are each larger than 200 MB in size. The company needs a data access solution that offers the shortest processing time and the least amount of setup. Which solution will meet these requirements?

   • AUse File mode in SageMaker to copy the dataset from the S3 buckets to the ML instance storage.
   • BCreate an Amazon FSx for Lustre file system. Link the file system to the S3 buckets.
   • CCreate an Amazon Elastic File System (Amazon EFS) file system. Mount the file system to the training instances.
   • DUse FastFile mode in SageMaker to stream the files on demand from the S3 buckets.

   Show answer

   Answer: D

   Explanation

   When to use fast file mode: For larger datasets with larger files (more than 50 MB per file), the first option is to try fast file mode, which is more straightforward to use than FSx for Lustre because it doesn't require creating a file system, or connecting to a VPC. Fast file mode is ideal for large file containers (more than 150 MB), and might also do well with files more than 50 MB. https://docs.aws.amazon.com/sagemaker/latest/dg/model-access-training-data.html#model-access-training-data-best-practices

   Source: Adapted from community discussion — mawsman

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

2. Question 152 · 368 in bank

   An online store is predicting future book sales by using a linear regression model that is based on past sales data. The data includes duration, a numerical feature that represents the number of days that a book has been listed in the online store. A data scientist performs an exploratory data analysis and discovers that the relationship between book sales and duration is skewed and non-linear. Which data transformation step should the data scientist take to improve the predictions of the model?

   • AOne-hot encoding
   • BCartesian product transformation
   • CQuantile binning
   • DNormalization

   Show answer

   Answer: C

   Explanation

   C. Quantile binning: Quantile binning (or discretization) involves dividing a continuous variable into bins based on quantiles. This can be useful for handling skewed data by distributing the data more evenly across the bins. However, this method transforms the numerical feature into a categorical one, which might not be ideal for preserving the ordinal nature and the detailed variance of the 'duration' feature in a regression model. If the choice must be made from the given options, Option C (Quantile binning) might be the most suitable, albeit not ideal, as it can at least help in dealing with skewed distributions by distributing the data across bins more evenly. However, the data scientist should consider logarithmic or polynomial transformations for a more direct approach to addressing non-linearity.

   Source: Adapted from community discussion — CloudHandsOn

   References

   • AWS documentation

   Next question

3. Question 153 · 368 in bank

   A company's data engineer wants to use Amazon S3 to share datasets with data scientists. The data scientists work in three departments: Finance. Marketing, and Human Resources. Each department has its own IAM user group. Some datasets contain sensitive information and should be accessed only by the data scientists from the Finance department. How can the data engineer set up access to meet these requirements?

   • ACreate an S3 bucket for each dataset. Create an ACL for each S3 bucket. For each S3 bucket that contains a sensitive dataset, set the ACL to allow access only from the Finance department user group. Allow all three department user groups to access each S3 bucket that contains a non-sensitive dataset.
   • BCreate an S3 bucket for each dataset. For each S3 bucket that contains a sensitive dataset, set the bucket policy to allow access only from the Finance department user group. Allow all three department user groups to access each S3 bucket that contains a non-sensitive dataset.
   • CCreate a single S3 bucket that includes two folders to separate the sensitive datasets from the non-sensitive datasets. For the Finance department user group, attach an IAM policy that provides access to both folders. For the Marketing and Human Resources department user groups, attach an IAM policy that provides access to only the folder that contains the non-sensitive datasets.
   • DCreate a single S3 bucket that includes two folders to separate the sensitive datasets from the non-sensitive datasets. Set the policy for the S3 bucket to allow only the Finance department user group to access the folder that contains the sensitive datasets. Allow all three department user groups to access the folder that contains the non-sensitive datasets.

   Show answer

   Answer: C

   Explanation

   You cannot identify a user group as a principal in a policy (such as a resource-based policy) because groups relate to permissions, not authentication, and principals are authenticated IAM entities. an Amazon S3 bucket policy cannot have a user group as the principal directly. https://docs.aws.amazon.com/IAM/latest/UserGuide/reference_policies_elements_principal.html I stand corrected. I retract my previous answer.

   Source: Adapted from community discussion — geoan13

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

4. Question 154 · 368 in bank

   A company operates an amusement park. The company wants to collect, monitor, and store real-time traffic data at several park entrances by using strategically placed cameras. The company’s security team must be able to immediately access the data for viewing. Stored data must be indexed and must be accessible to the company’s data science team. Which solution will meet these requirements MOST cost-effectively?

   • AUse Amazon Kinesis Video Streams to ingest, index, and store the data. Use the built-in integration with Amazon Rekognition for viewing by the security team.
   • BUse Amazon Kinesis Video Streams to ingest, index, and store the data. Use the built-in HTTP live streaming (HLS) capability for viewing by the security team.
   • CUse Amazon Rekognition Video and the GStreamer plugin to ingest the data for viewing by the security team. Use Amazon Kinesis Data Streams to index and store the data.
   • DUse Amazon Kinesis Data Firehose to ingest, index, and store the data. Use the built-in HTTP live streaming (HLS) capability for viewing by the security team.

   Show answer

   Answer: B

   Explanation

   Amazon Kinesis Video Streams is a fully managed service that makes it easy to ingest, store, and analyze streaming video data. The built-in HTTP live streaming (HLS) capability allows the security team to view the data in real time. Amazon Kinesis Video Streams is a pay-per-use service, so the company will only be charged for the amount of data that it ingests, stores, and analyzes.

   Source: Adapted from community discussion — Mickey321

   References

   • AWS documentation

   Next question

5. Question 155 · 368 in bank

   An engraving company wants to automate its quality control process for plaques. The company performs the process before mailing each customized plaque to a customer. The company has created an Amazon S3 bucket that contains images of defects that should cause a plaque to be rejected. Low-confidence predictions must be sent to an internal team of reviewers who are using Amazon Augmented AI (Amazon A2I). Which solution will meet these requirements?

   • AUse Amazon Textract for automatic processing. Use Amazon A2I with Amazon Mechanical Turk for manual review.
   • BUse Amazon Rekognition for automatic processing. Use Amazon A2I with a private workforce option for manual review.
   • CUse Amazon Transcribe for automatic processing. Use Amazon A2I with a private workforce option for manual review.
   • DUse AWS Panorama for automatic processing. Use Amazon A2I with Amazon Mechanical Turk for manual review.

   Show answer

   Answer: B

   Explanation

   Amazon Rekognition is an image and video analysis service that can detect objects, scenes, and faces in images. The company can use Amazon Rekognition to automatically process images of plaques and identify defects that should cause a plaque to be rejected. Low-confidence predictions can be sent to an internal team of reviewers who are using Amazon A2I with a private workforce option for manual review. This will ensure that the plaques are thoroughly checked before being mailed to customers A is not suitable because Amazon Textract is a service that extracts text and data from scanned documents. It is not designed for image analysis. C is also not suitable because Amazon Transcribe is a service that converts speech to text. It is not designed for image analysis. D is not suitable because AWS Panorama is a computer vision service that runs on cameras and other edge devices. It is not designed for analyzing images stored in an S3 bucket

   Source: Adapted from community discussion — teka112233

   Next question

6. Question 156 · 368 in bank

   A Machine Learning Specialist trained a regression model, but the first iteration needs optimizing. The Specialist needs to understand whether the model is more frequently overestimating or underestimating the target. What option can the Specialist use to determine whether it is overestimating or underestimating the target value?

   • ARoot Mean Square Error (RMSE)
   • BResidual plots
   • CArea under the curve
   • DConfusion matrix

   Show answer

   Answer: B

   Explanation

   RMSE says about the error value but not the sign of error. The question is to find whether the model overestimates or underestimates - I guess residual plots clearly show that answer B

   Source: Adapted from community discussion — vetal

   References

   • AWS documentation
   • AWS documentation

   Next question

7. Question 157 · 368 in bank

   A machine learning (ML) engineer at a bank is building a data ingestion solution to provide transaction features to financial ML models. Raw transactional data is available in an Amazon Kinesis data stream. The solution must compute rolling averages of the ingested data from the data stream and must store the results in Amazon SageMaker Feature Store. The solution also must serve the results to the models in near real time. Which solution will meet these requirements?

   • ALoad the data into an Amazon S3 bucket by using Amazon Kinesis Data Firehose. Use a SageMaker Processing job to aggregate the data and to load the results into SageMaker Feature Store as an online feature group.
   • BWrite the data directly from the data stream into SageMaker Feature Store as an online feature group. Calculate the rolling averages in place within SageMaker Feature Store by using the SageMaker GetRecord API operation.
   • CConsume the data stream by using an Amazon Kinesis Data Analytics SQL application that calculates the rolling averages. Generate a result stream. Consume the result stream by using a custom AWS Lambda function that publishes the results to SageMaker Feature Store as an online feature group.
   • DLoad the data into an Amazon S3 bucket by using Amazon Kinesis Data Firehose. Use a SageMaker Processing job to load the data into SageMaker Feature Store as an offline feature group. Compute the rolling averages at query time.

   Show answer

   Answer: C

   Explanation

   A. NO - no need for intermediary S3 storage B. NO - Feature store does not have built-in transformations C. YES - https://aws.amazon.com/blogs/machine-learning/using-streaming-ingestion-with-amazon-sagemaker-feature-store-to-make-ml-backed-decisions-in-near-real-time/ D. NO - Computing a query time is expensive, you want it done once and cached

   Source: Adapted from community discussion — loict

   References

   • AWS documentation

   Next question

8. Question 158 · 368 in bank

   Each morning, a data scientist at a rental car company creates insights about the previous day’s rental car reservation demands. The company needs to automate this process by streaming the data to Amazon S3 in near real time. The solution must detect high-demand rental cars at each of the company’s locations. The solution also must create a visualization dashboard that automatically refreshes with the most recent data. Which solution will meet these requirements with the LEAST development time?

   • AUse Amazon Kinesis Data Firehose to stream the reservation data directly to Amazon S3. Detect high-demand outliers by using Amazon QuickSight ML Insights. Visualize the data in QuickSight.
   • BUse Amazon Kinesis Data Streams to stream the reservation data directly to Amazon S3. Detect high-demand outliers by using the Random Cut Forest (RCF) trained model in Amazon SageMaker. Visualize the data in Amazon QuickSight.
   • CUse Amazon Kinesis Data Firehose to stream the reservation data directly to Amazon S3. Detect high-demand outliers by using the Random Cut Forest (RCF) trained model in Amazon SageMaker. Visualize the data in Amazon QuickSight.
   • DUse Amazon Kinesis Data Streams to stream the reservation data directly to Amazon S3. Detect high-demand outliers by using Amazon QuickSight ML Insights. Visualize the data in QuickSight.

   Show answer

   Answer: A

   Explanation

   A. YES - Quicksight has Z-score algorithm to detect outliers B. NO - Kinesis Data Streams cannot stream directly to Amazon S3. C. NO - RCF is overkill when QuickSight supports D. NO - Kinesis Data Streams cannot stream directly to Amazon S3.

   Source: Adapted from community discussion — loict

   References

   • AWS documentation

   Next question

9. Question 159 · 368 in bank

   A machine learning (ML) engineer is integrating a production model with a customer metadata repository for real-time inference. The repository is hosted in Amazon SageMaker Feature Store. The engineer wants to retrieve only the latest version of the customer metadata record for a single customer at a time. Which solution will meet these requirements?

   • AUse the SageMaker Feature Store BatchGetRecord API with the record identifier. Filter to find the latest record.
   • BCreate an Amazon Athena query to retrieve the data from the feature table.
   • CCreate an Amazon Athena query to retrieve the data from the feature table. Use the write_time value to find the latest record.
   • DUse the SageMaker Feature Store GetRecord API with the record identifier.

   Show answer

   Answer: D

   Explanation

   D. Using the SageMaker Feature Store GetRecord API with the record identifier1. This API allows customers to retrieve features from a single feature group and access one record per API call2. The record identifier is a unique value that identifies a record within a feature group1. The GetRecord API returns the latest version of the record by default1. This solution avoids the need to use additional queries or filters to find the latest record.

   Source: Adapted from community discussion — Mickey321

   References

   • AWS documentation

   Next question

10. Question 160 · 368 in bank

    Select 2

    A company’s data scientist has trained a new machine learning model that performs better on test data than the company’s existing model performs in the production environment. The data scientist wants to replace the existing model that runs on an Amazon SageMaker endpoint in the production environment. However, the company is concerned that the new model might not work well on the production environment data. The data scientist needs to perform A/B testing in the production environment to evaluate whether the new model performs well on production environment data. Which combination of steps must the data scientist take to perform the A/B testing? (Choose two.)

    • ACreate a new endpoint configuration that includes a production variant for each of the two models.
    • BCreate a new endpoint configuration that includes two target variants that point to different endpoints.
    • CDeploy the new model to the existing endpoint.
    • DUpdate the existing endpoint to activate the new model.
    • EUpdate the existing endpoint to use the new endpoint configuration.

    Show answer

    Answer: AE

    Explanation

    A. YES - we create a new configuration with 2 production variants (1) B. Create a new endpoint configuration that includes two target variants that point to different endpoints. C. NO - that would defeat A D. NO - that would defeat A E. YES - we modify the existing endpoint to now the new configuration (2)

    Source: Adapted from community discussion — loict

    References

    • AWS documentation
    • AWS documentation

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

MLS-C01 practice, question 151. 368 questions available.