MLS-C01 practice questions 11–20

1. Question 11 · 368 in bank

   A data scientist is developing a pipeline to ingest streaming web traffic data. The data scientist needs to implement a process to identify unusual web traffic patterns as part of the pipeline. The patterns will be used downstream for alerting and incident response. The data scientist has access to unlabeled historic data to use, if needed. The solution needs to do the following: ✑ Calculate an anomaly score for each web traffic entry. Adapt unusual event identification to changing web patterns over time.

   

   Which approach should the data scientist implement to meet these requirements?

   • AUse historic web traffic data to train an anomaly detection model using the Amazon SageMaker Random Cut Forest (RCF) built-in model. Use an Amazon Kinesis Data Stream to process the incoming web traffic data. Attach a preprocessing AWS Lambda function to perform data enrichment by calling the RCF model to calculate the anomaly score for each record.
   • BUse historic web traffic data to train an anomaly detection model using the Amazon SageMaker built-in XGBoost model. Use an Amazon Kinesis Data Stream to process the incoming web traffic data. Attach a preprocessing AWS Lambda function to perform data enrichment by calling the XGBoost model to calculate the anomaly score for each record.
   • CCollect the streaming data using Amazon Kinesis Data Firehose. Map the delivery stream as an input source for Amazon Kinesis Data Analytics. Write a SQL query to run in real time against the streaming data with the k-Nearest Neighbors (kNN) SQL extension to calculate anomaly scores for each record using a tumbling window.
   • DCollect the streaming data using Amazon Kinesis Data Firehose. Map the delivery stream as an input source for Amazon Kinesis Data Analytics. Write a SQL query to run in real time against the streaming data with the Amazon Random Cut Forest (RCF) SQL extension to calculate anomaly scores for each record using a sliding window.

   Show answer

   Answer: D

   Explanation

   D uses the built-in RCF algorithm, which is designed for anomaly detection on streaming data and can adapt to changing patterns over time.It does not require any training data or preprocessing steps, as the RCF algorithm can learn from the streaming data directly. It uses a sliding window, which allows for continuous updating of the anomaly scores based on the most recent data points. It leverages the Amazon Kinesis Data Analytics service, which provides a scalable and managed platform for running SQL queries on streaming data. Option A requires training an RCF model on historic data, which may not reflect the current web traffic patterns. It also adds complexity and latency by invoking a Lambda function for each record.

   Source: Adapted from community discussion — Mickey321

   References

   • AWS documentation
   • AWS documentation

   Next question

2. Question 12 · 368 in bank

   A Data Scientist received a set of insurance records, each consisting of a record ID, the final outcome among 200 categories, and the date of the final outcome. Some partial information on claim contents is also provided, but only for a few of the 200 categories. For each outcome category, there are hundreds of records distributed over the past 3 years. The Data Scientist wants to predict how many claims to expect in each category from month to month, a few months in advance. What type of machine learning model should be used?

   • AClassification month-to-month using supervised learning of the 200 categories based on claim contents.
   • BReinforcement learning using claim IDs and timestamps where the agent will identify how many claims in each category to expect from month to month.
   • CForecasting using claim IDs and timestamps to identify how many claims in each category to expect from month to month.
   • DClassification with supervised learning of the categories for which partial information on claim contents is provided, and forecasting using claim IDs and timestamps for all other categories.

   Show answer

   Answer: C

   Explanation

   I think it should be C as the final outcome among 200 categories is already know. No need to build a classification model. It's pure forecasting problem.

   Source: Adapted from community discussion — JBX2010

   Next question

3. Question 13 · 368 in bank

   A Machine Learning Specialist receives customer data for an online shopping website. The data includes demographics, past visits, and locality information. The Specialist must develop a machine learning approach to identify the customer shopping patterns, preferences, and trends to enhance the website for better service and smart recommendations. Which solution should the Specialist recommend?

   • ALatent Dirichlet Allocation (LDA) for the given collection of discrete data to identify patterns in the customer database.
   • BA neural network with a minimum of three layers and random initial weights to identify patterns in the customer database.
   • CCollaborative filtering based on user interactions and correlations to identify patterns in the customer database.
   • DRandom Cut Forest (RCF) over random subsamples to identify patterns in the customer database.

   Show answer

   Answer: C

   Explanation

   Not convinced with A. Answer C seems to be a better fit than A for recommendation model (LDA appears to be a topic-based model on unavailable data with similar patterns) https://aws.amazon.com/blogs/machine-learning/extending-amazon-sagemaker-factorization-machines-algorithm-to-predict-top-x-recommendations/

   Source: Adapted from community discussion — rsimham

   References

   • AWS documentation
   • AWS documentation

   Next question

4. Question 14 · 368 in bank

   A company that promotes healthy sleep patterns by providing cloud-connected devices currently hosts a sleep tracking application on AWS. The application collects device usage information from device users. The company's Data Science team is building a machine learning model to predict if and when a user will stop utilizing the company's devices. Predictions from this model are used by a downstream application that determines the best approach for contacting users. The Data Science team is building multiple versions of the machine learning model to evaluate each version against the company's business goals. To measure long-term effectiveness, the team wants to run multiple versions of the model in parallel for long periods of time, with the ability to control the portion of inferences served by the models. Which solution satisfies these requirements with MINIMAL effort?

   • ABuild and host multiple models in Amazon SageMaker. Create multiple Amazon SageMaker endpoints, one for each model. Programmatically control invoking different models for inference at the application layer.
   • BBuild and host multiple models in Amazon SageMaker. Create an Amazon SageMaker endpoint configuration with multiple production variants. Programmatically control the portion of the inferences served by the multiple models by updating the endpoint configuration.
   • CBuild and host multiple models in Amazon SageMaker Neo to take into account different types of medical devices. Programmatically control which model is invoked for inference based on the medical device type.
   • DBuild and host multiple models in Amazon SageMaker. Create a single endpoint that accesses multiple models. Use Amazon SageMaker batch transform to control invoking the different models through the single endpoint.

   Show answer

   Answer: B

   Explanation

   B is the correct answer. A/B testing with Amazon SageMaker is required in the Exam. In A/B testing, you test different variants of your models and compare how each variant performs. Amazon SageMaker enables you to test multiple models or model versions behind the `same endpoint` using `production variants`. Each production variant identifies a machine learning (ML) model and the resources deployed for hosting the model. To test multiple models by `distributing traffic` between them, specify the `percentage of the traffic` that gets routed to each model by specifying the `weight` for each `production variant` in the endpoint configuration.

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation
   • AWS documentation

   Next question

5. Question 15 · 368 in bank

   An agricultural company is interested in using machine learning to detect specific types of weeds in a 100-acre grassland field. Currently, the company uses tractor-mounted cameras to capture multiple images of the field as 10 ֳ— 10 grids. The company also has a large training dataset that consists of annotated images of popular weed classes like broadleaf and non-broadleaf docks. The company wants to build a weed detection model that will detect specific types of weeds and the location of each type within the field. Once the model is ready, it will be hosted on Amazon SageMaker endpoints. The model will perform real-time inferencing using the images captured by the cameras. Which approach should a Machine Learning Specialist take to obtain accurate predictions?

   • APrepare the images in RecordIO format and upload them to Amazon S3. Use Amazon SageMaker to train, test, and validate the model using an image classification algorithm to categorize images into various weed classes.
   • BPrepare the images in Apache Parquet format and upload them to Amazon S3. Use Amazon SageMaker to train, test, and validate the model using an object- detection single-shot multibox detector (SSD) algorithm.
   • CPrepare the images in RecordIO format and upload them to Amazon S3. Use Amazon SageMaker to train, test, and validate the model using an object- detection single-shot multibox detector (SSD) algorithm.
   • DPrepare the images in Apache Parquet format and upload them to Amazon S3. Use Amazon SageMaker to train, test, and validate the model using an image classification algorithm to categorize images into various weed classes.

   Show answer

   Answer: C

   Explanation

   C is my answer. Pay attention that the question is asking for 2 things: 1. detect specific types of weeds 2. detect the location of each type within the field. Image Classification can only classify images. Object detection algorithm: 1.identifies all instances of objects within the image scene. 2.its location and scale in the image are indicated by a rectangular bounding box. Data format for Computer Vision algorithms in SageMaker: Recommend to use RecordIO.

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation

   Next question

6. Question 16 · 368 in bank

   A manufacturer is operating a large number of factories with a complex supply chain relationship where unexpected downtime of a machine can cause production to stop at several factories. A data scientist wants to analyze sensor data from the factories to identify equipment in need of preemptive maintenance and then dispatch a service team to prevent unplanned downtime. The sensor readings from a single machine can include up to 200 data points including temperatures, voltages, vibrations, RPMs, and pressure readings. To collect this sensor data, the manufacturer deployed Wi-Fi and LANs across the factories. Even though many factory locations do not have reliable or high- speed internet connectivity, the manufacturer would like to maintain near-real-time inference capabilities. Which deployment architecture for the model will address these business requirements?

   • ADeploy the model in Amazon SageMaker. Run sensor data through this model to predict which machines need maintenance.
   • BDeploy the model on AWS IoT Greengrass in each factory. Run sensor data through this model to infer which machines need maintenance.
   • CDeploy the model to an Amazon SageMaker batch transformation job. Generate inferences in a daily batch report to identify machines that need maintenance.
   • DDeploy the model in Amazon SageMaker and use an IoT rule to write data to an Amazon DynamoDB table. Consume a DynamoDB stream from the table with an AWS Lambda function to invoke the endpoint.

   Show answer

   Answer: B

   Explanation

   B is my answer. For latency-sensitive use cases and for use-cases that require analyzing large amounts of streaming data, it may not be possible to run ML inference in the cloud. Besides, cloud-connectivity may not be available all the time. For these use cases, you need to deploy the ML model close to the data source. SageMaker Neo + IoT GreenGrass To design and push something to edge: 1. design something to do the job, say TF model 2. compile it for the edge device using SageMaker Neo, say Nvidia Jetson 3. run it on the edge using IoT GreenGrass

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation
   • AWS documentation

   Next question

7. Question 17 · 368 in bank

   A Machine Learning Specialist is designing a scalable data storage solution for Amazon SageMaker. There is an existing TensorFlow-based model implemented as a train.py script that relies on static training data that is currently stored as TFRecords. Which method of providing training data to Amazon SageMaker would meet the business requirements with the LEAST development overhead?

   • AUse Amazon SageMaker script mode and use train.py unchanged. Point the Amazon SageMaker training invocation to the local path of the data without reformatting the training data.
   • BUse Amazon SageMaker script mode and use train.py unchanged. Put the TFRecord data into an Amazon S3 bucket. Point the Amazon SageMaker training invocation to the S3 bucket without reformatting the training data.
   • CRewrite the train.py script to add a section that converts TFRecords to protobuf and ingests the protobuf data instead of TFRecords.
   • DPrepare the data in the format accepted by Amazon SageMaker. Use AWS Glue or AWS Lambda to reformat and store the data in an Amazon S3 bucket.

   Show answer

   Answer: B

   Explanation

   Unfortunilty you can't use the script unchanged, there are some things that need to be added: 1. Make sure your script can handle --model_dir as an additional command line argument. If you did not specify a location when you created the TensorFlow estimator, an S3 location under the default training job bucket is used. Distributed training with parameter servers requires you to use the tf.estimator.train_and_evaluate API and to provide an S3 location as the model directory during training. 2. Load input data from the input channels. The input channels are defined when fit is called. ## https://sagemaker.readthedocs.io/en/stable/frameworks/tensorflow/using_tf.html Beause of the pre-rec Ans A and B are an easy disqualifcation. There is no need to change the training format so option C is a red herring Ans is D Not the most obvious answer

   Source: Adapted from community discussion — cnethers

   References

   • AWS documentation

   Next question

8. Question 18 · 368 in bank

   The chief editor for a product catalog wants the research and development team to build a machine learning system that can be used to detect whether or not individuals in a collection of images are wearing the company's retail brand. The team has a set of training data. Which machine learning algorithm should the researchers use that BEST meets their requirements?

   • ALatent Dirichlet Allocation (LDA)
   • BRecurrent neural network (RNN)
   • CK-means
   • DConvolutional neural network (CNN)

   Show answer

   Answer: D

   Explanation

   D is the correct Well, I did those exams topics questions for 2 weeks and still easier compared to Maarek exams that simulate AWS MLS. Is that correct? Can I expect the exam to be easier as it's in exams topics?

   Source: Adapted from community discussion — kaike_reis

   Next question

9. Question 19 · 368 in bank

   A retail company is using Amazon Personalize to provide personalized product recommendations for its customers during a marketing campaign. The company sees a significant increase in sales of recommended items to existing customers immediately after deploying a new solution version, but these sales decrease a short time after deployment. Only historical data from before the marketing campaign is available for training. How should a data scientist adjust the solution?

   • AUse the event tracker in Amazon Personalize to include real-time user interactions.
   • BAdd user metadata and use the HRNN-Metadata recipe in Amazon Personalize.
   • CImplement a new solution using the built-in factorization machines (FM) algorithm in Amazon SageMaker.
   • DAdd event type and event value fields to the interactions dataset in Amazon Personalize.

   Show answer

   Answer: A

   Explanation

   A is the correct answer. Because in this case, it is not the problem with the existing historical data (event value, event type(click or not)), the sales do not keep growing and now you need to obtain more recent interactive data. An event tracker specifies a destination dataset group for new event data.

   Source: Adapted from community discussion — SophieSu

   References

   • AWS documentation
   • AWS documentation

   Next question

10. Question 20 · 368 in bank

    Select 2

    A machine learning (ML) specialist wants to secure calls to the Amazon SageMaker Service API. The specialist has configured Amazon VPC with a VPC interface endpoint for the Amazon SageMaker Service API and is attempting to secure traffic from specific sets of instances and IAM users. The VPC is configured with a single public subnet. Which combination of steps should the ML specialist take to secure the traffic? (Choose two.)

    • AAdd a VPC endpoint policy to allow access to the IAM users.
    • BModify the users' IAM policy to allow access to Amazon SageMaker Service API calls only.
    • CModify the security group on the endpoint network interface to restrict access to the instances.
    • DModify the ACL on the endpoint network interface to restrict access to the instances.
    • EAdd a SageMaker Runtime VPC endpoint interface to the VPC.

    Show answer

    Answer: AC

    Explanation

    A - VPC endpoint policy can limit the access to specific group of user/roles Not B - setting iam user policy can limit user access other aws service but not secure the traffic C - “specific” sets of instances - means security rules in instance level Not D - ACL (access control list) allows or denies specific inbound or outbound traffic at the subnet level. Not E - VPC is configured with public subnet, adding interface without limit the traffic means not secure

    Source: Adapted from community discussion — wisoxe8356

    References

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

    Next question

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

MLS-C01 practice, question 11. 368 questions available.