MLS-C01 practice questions 61–70

1. Question 61 · 368 in bank

   A machine learning specialist needs to analyze comments on a news website with users across the globe. The specialist must find the most discussed topics in the comments that are in either English or Spanish. What steps could be used to accomplish this task? (Choose two.)

   • AUse an Amazon SageMaker BlazingText algorithm to find the topics independently from language. Proceed with the analysis.
   • BUse an Amazon SageMaker seq2seq algorithm to translate from Spanish to English, if necessary. Use a SageMaker Latent Dirichlet Allocation (LDA) algorithm to find the topics.
   • CUse Amazon Translate to translate from Spanish to English, if necessary. Use Amazon Comprehend topic modeling to find the topics.
   • DUse Amazon Translate to translate from Spanish to English, if necessary. Use Amazon Lex to extract topics form the content.
   • EUse Amazon Translate to translate from Spanish to English, if necessary. Use Amazon SageMaker Neural Topic Model (NTM) to find the topics.

   Show answer

   Answer: C

   Explanation

   C and E Amazon comprehend topic modeling can be unspervised. https://docs.aws.amazon.com/comprehend/latest/dg/topic-modeling.html You can use Amazon Comprehend to examine the content of a collection of documents to determine common themes. For example, you can give Amazon Comprehend a collection of news articles, and it will determine the subjects, such as sports, politics, or entertainment. The text in the documents doesn't need to be annotated.

   Source: Adapted from community discussion — rjekstein

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

2. Question 62 · 368 in bank

   A machine learning (ML) specialist is administering a production Amazon SageMaker endpoint with model monitoring configured. Amazon SageMaker Model Monitor detects violations on the SageMaker endpoint, so the ML specialist retrains the model with the latest dataset. This dataset is statistically representative of the current production traffic. The ML specialist notices that even after deploying the new SageMaker model and running the first monitoring job, the SageMaker endpoint still has violations. What should the ML specialist do to resolve the violations?

   • AManually trigger the monitoring job to re-evaluate the SageMaker endpoint traffic sample.
   • BRun the Model Monitor baseline job again on the new training set. Configure Model Monitor to use the new baseline.
   • CDelete the endpoint and recreate it with the original configuration.
   • DRetrain the model again by using a combination of the original training set and the new training set.

   Show answer

   Answer: B

   Explanation

   B. Run the Model Monitor baseline job again on the new training set: This is a key step after retraining the model. Since the model has been retrained with a new dataset, the baseline against which its predictions are compared should also be updated. Running the baseline job again on the new training set and configuring Model Monitor to use this new baseline will ensure that the monitoring is relevant to the current state of the model and the data it's processing. D. Retrain the model again with a combination of the original and new training sets: While retraining the model can be a good approach in some scenarios, there's no indication in this case that the issue lies with the model's performance itself. The issue seems to be with the Model Monitor's baseline not aligning with the current model.

   Source: Adapted from community discussion — CloudHandsOn

   References

   • AWS documentation
   • AWS documentation

   Next question

3. Question 63 · 368 in bank

   Select 2

   A company supplies wholesale clothing to thousands of retail stores. A data scientist must create a model that predicts the daily sales volume for each item for each store. The data scientist discovers that more than half of the stores have been in business for less than 6 months. Sales data is highly consistent from week to week. Daily data from the database has been aggregated weekly, and weeks with no sales are omitted from the current dataset. Five years (100 MB) of sales data is available in Amazon S3. Which factors will adversely impact the performance of the forecast model to be developed, and which actions should the data scientist take to mitigate them? (Choose two.)

   • ADetecting seasonality for the majority of stores will be an issue. Request categorical data to relate new stores with similar stores that have more historical data.
   • BThe sales data does not have enough variance. Request external sales data from other industries to improve the model's ability to generalize.
   • CSales data is aggregated by week. Request daily sales data from the source database to enable building a daily model.
   • DThe sales data is missing zero entries for item sales. Request that item sales data from the source database include zero entries to enable building the model.
   • EOnly 100 MB of sales data is available in Amazon S3. Request 10 years of sales data, which would provide 200 MB of training data for the model.

   Show answer

   Answer: AC

   Explanation

   AC would be my answer. As half the stores have only been open for 6 months, no seasonality would be captured. The aggregation of the daily also removes trends we see during the week which is also not great when we are looking for the daily predicated sales figure

   Source: Adapted from community discussion — cron0001

   Next question

4. Question 64 · 368 in bank

   Select 3

   An ecommerce company is automating the categorization of its products based on images. A data scientist has trained a computer vision model using the Amazon SageMaker image classification algorithm. The images for each product are classified according to specific product lines. The accuracy of the model is too low when categorizing new products. All of the product images have the same dimensions and are stored within an Amazon S3 bucket. The company wants to improve the model so it can be used for new products as soon as possible. Which steps would improve the accuracy of the solution? (Choose three.)

   • AUse the SageMaker semantic segmentation algorithm to train a new model to achieve improved accuracy.
   • BUse the Amazon Rekognition DetectLabels API to classify the products in the dataset.
   • CAugment the images in the dataset. Use open source libraries to crop, resize, flip, rotate, and adjust the brightness and contrast of the images.
   • DUse a SageMaker notebook to implement the normalization of pixels and scaling of the images. Store the new dataset in Amazon S3.
   • EUse Amazon Rekognition Custom Labels to train a new model.
   • FCheck whether there are class imbalances in the product categories, and apply oversampling or undersampling as required. Store the new dataset in Amazon S3.

   Show answer

   Answer: CDF

   Explanation

   The question asks for quick solutions and to improve the classifier's accuracy. Since we want a quick fix, I'm going to avoid solutions that requires a new model implementation. Therefore, the alternatives that can improve the performance of the current classification are: Letter F, C and D. Letters B and E would bring a new development cost from zero and Letter A does not solve the classification problem.

   Source: Adapted from community discussion — kaike_reis

   References

   • AWS documentation

   Next question

5. Question 65 · 368 in bank

   A data scientist is training a text classification model by using the Amazon SageMaker built-in BlazingText algorithm. There are 5 classes in the dataset, with 300 samples for category A, 292 samples for category B, 240 samples for category C, 258 samples for category D, and 310 samples for category E. The data scientist shuffles the data and splits off 10% for testing. After training the model, the data scientist generates confusion matrices for the training and test sets.

   

   

   What could the data scientist conclude form these results?

   • AClasses C and D are too similar.
   • BThe dataset is too small for holdout cross-validation.
   • CThe data distribution is skewed.
   • DThe model is overfitting for classes B and E.

   Show answer

   Answer: A

   Explanation

   the correct answer should be A, the model is clearly unable to tell C and D apart the reason why B is incorrect is subtle - there is holdout validation or cross-validation, but not holdout cross-validation; while I think it would be more reasonable to use CV with such a small dataset rather than holdout, the answer is mixing terms and therefore should be wrong also, the test set confusion matrix is still pretty comparable to the train set one, so I wouldn't say there is objective evidence to claim holdout is a wrong choice here

   Source: Adapted from community discussion — dolorez

   Next question

6. Question 66 · 368 in bank

   Select 3

   A company that manufactures mobile devices wants to determine and calibrate the appropriate sales price for its devices. The company is collecting the relevant data and is determining data features that it can use to train machine learning (ML) models. There are more than 1,000 features, and the company wants to determine the primary features that contribute to the sales price. Which techniques should the company use for feature selection? (Choose three.)

   • AData scaling with standardization and normalization
   • BCorrelation plot with heat maps
   • CData binning
   • DUnivariate selection
   • EFeature importance with a tree-based classifier
   • FData augmentation

   Show answer

   Answer: BDE

   Explanation

   i will go for B, D and E. B and D for me are like doing partial regression and corr plot can actually tell you briefly how well the univariate is correlated with your target and i guess that also apply for D.. and E , feature importance ranking that's what feature selection strategy want from my POV. And for Data Binning is data enrichment just like augmentations , but then the question was saying they want to do feature selection over 1k+ variables which implies they actually care more about which variable(s) can contribute more on determining the price ?

   Source: Adapted from community discussion — ckkobe24

   Next question

7. Question 67 · 368 in bank

   During mini-batch training of a neural network for a classification problem, a Data Scientist notices that training accuracy oscillates. What is the MOST likely cause of this issue?

   • AThe class distribution in the dataset is imbalanced.
   • BDataset shuffling is disabled.
   • CThe batch size is too big.
   • DThe learning rate is very high.

   Show answer

   Answer: D

   Explanation

   Answer is D. Should the weight be increased or reduced so that the error is smaller than the current value? You need to examine the amount of change to know that. Therefore, we differentiate and check whether the slope of the tangent is positive or negative, and update the weight value in the direction to reduce the error. The operation is repeated over and over so as to approach the optimal solution that is the goal. The width of the update amount is important at this time, and is determined by the learning rate.

   Source: Adapted from community discussion — gaku1016

   Next question

8. Question 68 · 368 in bank

   A power company wants to forecast future energy consumption for its customers in residential properties and commercial business properties. Historical power consumption data for the last 10 years is available. A team of data scientists who performed the initial data analysis and feature selection will include the historical power consumption data and data such as weather, number of individuals on the property, and public holidays. The data scientists are using Amazon Forecast to generate the forecasts. Which algorithm in Forecast should the data scientists use to meet these requirements?

   • AAutoregressive Integrated Moving Average (AIRMA)
   • BExponential Smoothing (ETS)
   • CConvolutional Neural Network - Quantile Regression (CNN-QR)
   • DProphet

   Show answer

   Answer: C

   Explanation

   CNN-QR is a deep learning algorithm that can model complex relationships between the inputs and outputs, such as the weather and public holidays, with historical power consumption data. CNN-QR has been shown to be effective in generating accurate predictions in many different types of forecasting use cases, including demand forecasting. ETS (Exponential Smoothing) is a classical time series algorithm that is often used for forecasting. It can be effective for simple time series data that have regular patterns, but may not be sufficient to handle the complexity of the given data. ARIMA (Autoregressive Integrated Moving Average) is another classical time series algorithm that can model complex patterns in data. However, it may be difficult to use in cases where there are many different inputs and the relationships between the inputs and outputs are complex.

   Source: Adapted from community discussion — AjoseO

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

9. Question 69 · 368 in bank

   A company wants to use automatic speech recognition (ASR) to transcribe messages that are less than 60 seconds long from a voicemail-style application. The company requires the correct identification of 200 unique product names, some of which have unique spellings or pronunciations. The company has 4,000 words of Amazon SageMaker Ground Truth voicemail transcripts it can use to customize the chosen ASR model. The company needs to ensure that everyone can update their customizations multiple times each hour. Which approach will maximize transcription accuracy during the development phase?

   • AUse a voice-driven Amazon Lex bot to perform the ASR customization. Create customer slots within the bot that specifically identify each of the required product names. Use the Amazon Lex synonym mechanism to provide additional variations of each product name as mis-transcriptions are identified in development.
   • BUse Amazon Transcribe to perform the ASR customization. Analyze the word confidence scores in the transcript, and automatically create or update a custom vocabulary file with any word that has a confidence score below an acceptable threshold value. Use this updated custom vocabulary file in all future transcription tasks.
   • CCreate a custom vocabulary file containing each product name with phonetic pronunciations, and use it with Amazon Transcribe to perform the ASR customization. Analyze the transcripts and manually update the custom vocabulary file to include updated or additional entries for those names that are not being correctly identified.
   • DUse the audio transcripts to create a training dataset and build an Amazon Transcribe custom language model. Analyze the transcripts and update the training dataset with a manually corrected version of transcripts where product names are not being transcribed correctly. Create an updated custom language model.

   Show answer

   Answer: C

   Explanation

   D is an ideal answer however, the question ask for "The company needs to ensure that everyone can update their customizations multiple times each hour". To retrain custom model each hour when we have changes, will be tedious and time consuming. I go with c, where we can ask everyone to just update the config file.

   Source: Adapted from community discussion — drcok87

   References

   • AWS documentation

   Next question

10. Question 70 · 368 in bank

    A company is building a demand forecasting model based on machine learning (ML). In the development stage, an ML specialist uses an Amazon SageMaker notebook to perform feature engineering during work hours that consumes low amounts of CPU and memory resources. A data engineer uses the same notebook to perform data preprocessing once a day on average that requires very high memory and completes in only 2 hours. The data preprocessing is not configured to use GPU. All the processes are running well on an ml.m5.4xlarge notebook instance. The company receives an AWS Budgets alert that the billing for this month exceeds the allocated budget. Which solution will result in the MOST cost savings?

    • AChange the notebook instance type to a memory optimized instance with the same vCPU number as the ml.m5.4xlarge instance has. Stop the notebook when it is not in use. Run both data preprocessing and feature engineering development on that instance.
    • BKeep the notebook instance type and size the same. Stop the notebook when it is not in use. Run data preprocessing on a P3 instance type with the same memory as the ml.m5.4xlarge instance by using Amazon SageMaker Processing.
    • CChange the notebook instance type to a smaller general purpose instance. Stop the notebook when it is not in use. Run data preprocessing on an ml.r5 instance with the same memory size as the ml.m5.4xlarge instance by using Amazon SageMaker Processing.
    • DChange the notebook instance type to a smaller general purpose instance. Stop the notebook when it is not in use. Run data preprocessing on an R5 instance with the same memory size as the ml.m5.4xlarge instance by using the Reserved Instance option.

    Show answer

    Answer: C

    Explanation

    I believe answer should be C. a) Initial processing needs less cpu and memory so that can be done on a smaller instance. b) Second operation is memory intensive so instance type should be changed to R5 type instance.

    Source: Adapted from community discussion — exam_prep

    References

    • AWS documentation

    Next question

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

MLS-C01 practice, question 61. 368 questions available.