MLS-C01 practice questions 231–240

1. Question 231 · 368 in bank

   A company uses sensors on devices such as motor engines and factory machines to measure parameters, temperature and pressure. The company wants to use the sensor data to predict equipment malfunctions and reduce services outages. Machine learning (ML) specialist needs to gather the sensors data to train a model to predict device malfunctions. The ML specialist must ensure that the data does not contain outliers before training the model. How can the ML specialist meet these requirements with the LEAST operational overhead?

   • ALoad the data into an Amazon SageMaker Studio notebook. Calculate the first and third quartile. Use a SageMaker Data Wrangler data flow to remove only values that are outside of those quartiles.
   • BUse an Amazon SageMaker Data Wrangler bias report to find outliers in the dataset. Use a Data Wrangler data flow to remove outliers based on the bias report.
   • CUse an Amazon SageMaker Data Wrangler anomaly detection visualization to find outliers in the dataset. Add a transformation to a Data Wrangler data flow to remove outliers.
   • DUse Amazon Lookout for Equipment to find and remove outliers from the dataset.

   Show answer

   Answer: C

   Explanation

   Anomaly detection visualization feature in SageMaker Data Wrangler is designed to identify outliers in the dataset based on sensor data parameters such as temperature and pressure. By visually inspecting the anomalies, the ML specialist can easily identify and remove outliers using transformations within Data Wrangler data flows, minimizing operational overhead.

   Source: Adapted from community discussion — AIWave

   References

   • AWS documentation

   Next question

2. Question 232 · 368 in bank

   A data scientist obtains a tabular dataset that contains 150 correlated features with different ranges to build a regression model. The data scientist needs to achieve more efficient model training by implementing a solution that minimizes impact on the model’s performance. The data scientist decides to perform a principal component analysis (PCA) preprocessing step to reduce the number of features to a smaller set of independent features before the data scientist uses the new features in the regression model. Which preprocessing step will meet these requirements?

   • AUse the Amazon SageMaker built-in algorithm for PCA on the dataset to transform the data.
   • BLoad the data into Amazon SageMaker Data Wrangler. Scale the data with a Min Max Scaler transformation step. Use the SageMaker built-in algorithm for PCA on the scaled dataset to transform the data.
   • CReduce the dimensionality of the dataset by removing the features that have the highest correlation. Load the data into Amazon SageMaker Data Wrangler. Perform a Standard Scaler transformation step to scale the data. Use the SageMaker built-in algorithm for PCA on the scaled dataset to transform the data.
   • DReduce the dimensionality of the dataset by removing the features that have the lowest correlation. Load the data into Amazon SageMaker Data Wrangler. Perform a Min Max Scaler transformation step to scale the data. Use the SageMaker built-in algorithm for PCA on the scaled dataset to transform the data.

   Show answer

   Answer: B

   Explanation

   A: No - PCA requires feature scaling to remove dominance of high value variables B: Yes - Scaling addresses the issue of features with different ranges + PCA does feature reduction C: No - manual removal may lead to removal of important features D: No - manual removal may lead to removal of important features

   Source: Adapted from community discussion — AIWave

   References

   • AWS documentation

   Next question

3. Question 233 · 368 in bank

   Select 2

   An online retailer collects the following data on customer orders: demographics, behaviors, location, shipment progress, and delivery time. A data scientist joins all the collected datasets. The result is a single dataset that includes 980 variables. The data scientist must develop a machine learning (ML) model to identify groups of customers who are likely to respond to a marketing campaign. Which combination of algorithms should the data scientist use to meet this requirement? (Choose two.)

   • ALatent Dirichlet Allocation (LDA)
   • BK-means
   • CSemantic segmentation
   • DPrincipal component analysis (PCA)
   • EFactorization machines (FM)

   Show answer

   Answer: BD

   Explanation

   B. K-means: This algorithm is effective for clustering customers into distinct groups based on similarities across their features, which can reveal segments more likely to respond to marketing campaigns. D. Principal Component Analysis (PCA): Given the high dimensionality of the dataset, PCA can reduce the number of variables to a manageable size while retaining most of the variance, making the dataset more tractable for clustering algorithms like K-means.

   Source: Adapted from community discussion — Alice1234

   Next question

4. Question 234 · 368 in bank

   A monitoring service generates 1 TB of scale metrics record data every minute. A Research team performs queries on this data using Amazon Athena. The queries run slowly due to the large volume of data, and the team requires better performance. How should the records be stored in Amazon S3 to improve query performance?

   • ACSV files
   • BParquet files
   • CCompressed JSON
   • DRecordIO

   Show answer

   Answer: B

   Explanation

   You can improve the performance of your query by compressing, partitioning, or converting your data into columnar formats. Amazon Athena supports open source columnar data formats such as Apache Parquet and Apache ORC. Converting your data into a compressed, columnar format lowers your cost and improves query performance by enabling Athena to scan less data from S3 when executing your query

   Source: Adapted from community discussion — emailtorajivk

   References

   • AWS documentation

   Next question

5. Question 235 · 368 in bank

   A machine learning engineer is building a bird classification model. The engineer randomly separates a dataset into a training dataset and a validation dataset. During the training phase, the model achieves very high accuracy. However, the model did not generalize well during validation of the validation dataset. The engineer realizes that the original dataset was imbalanced. What should the engineer do to improve the validation accuracy of the model?

   • APerform stratified sampling on the original dataset.
   • BAcquire additional data about the majority classes in the original dataset.
   • CUse a smaller, randomly sampled version of the training dataset.
   • DPerform systematic sampling on the original dataset.

   Show answer

   Answer: A

   Explanation

   A: Yes - Stratified sampling ensures that each class is proportionally represented and mitigates the impact of class imbalance on model performance B: No - additional data about the majority classes does not solve class imbalance issue C: No - Does not solve class imbalance issue and may worsen the situation D: No - selecting data points at regular intervals does not solve class imbalance issue

   Source: Adapted from community discussion — AIWave

   References

   • AWS documentation

   Next question

6. Question 236 · 368 in bank

   A data engineer wants to perform exploratory data analysis (EDA) on a petabyte of data. The data engineer does not want to manage compute resources and wants to pay only for queries that are run. The data engineer must write the analysis by using Python from a Jupyter notebook. Which solution will meet these requirements?

   • AUse Apache Spark from within Amazon Athena.
   • BUse Apache Spark from within Amazon SageMaker.
   • CUse Apache Spark from within an Amazon EMR cluster.
   • DUse Apache Spark through an integration with Amazon Redshift.

   Show answer

   Answer: A

   Explanation

   Amazon Athena makes it easy to interactively run data analytics and exploration using Apache Spark without the need to plan for, configure, or manage resources reference :-https://docs.aws.amazon.com/athena/latest/ug/notebooks-spark.html

   Source: Adapted from community discussion — 587df71

   References

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

   Next question

7. Question 237 · 368 in bank

   A data scientist receives a new dataset in .csv format and stores the dataset in Amazon S3. The data scientist will use the dataset to train a machine learning (ML) model. The data scientist first needs to identify any potential data quality issues in the dataset. The data scientist must identify values that are missing or values that are not valid. The data scientist must also identify the number of outliers in the dataset. Which solution will meet these requirements with the LEAST operational effort?

   • ACreate an AWS Glue job to transform the data from .csv format to Apache Parquet format. Use an AWS Glue crawler and Amazon Athena with appropriate SQL queries to retrieve the required information.
   • BLeave the dataset in .csv format. Use an AWS Glue crawler and Amazon Athena with appropriate SQL queries to retrieve the required information.
   • CCreate an AWS Glue job to transform the data from .csv format to Apache Parquet format. Import the data into Amazon SageMaker Data Wrangler. Use the Data Quality and Insights Report to retrieve the required information.
   • DLeave the dataset in .csv format. Import the data into Amazon SageMaker Data Wrangler. Use the Data Quality and Insights Report to retrieve the required information.

   Show answer

   Answer: D

   Explanation

   A: No - more manual/operational overhead B: No - more manual/operational overhead C: No - Data transformation to parquet requires more unnecessary operational overhead D: Yes - least operational effort - wrangler has built-in identification of data quality issues and outliers

   Source: Adapted from community discussion — AIWave

   Next question

8. Question 238 · 368 in bank

   An ecommerce company has developed a XGBoost model in Amazon SageMaker to predict whether a customer will return a purchased item. The dataset is imbalanced. Only 5% of customers return items. A data scientist must find the hyperparameters to capture as many instances of returned items as possible. The company has a small budget for compute. How should the data scientist meet these requirements MOST cost-effectively?

   • ATune all possible hyperparameters by using automatic model tuning (AMT). Optimize on {"HyperParameterTuningJobObjective": {"MetricName": "validation:accuracy", "Type": "Maximize"}}.
   • BTune the csv_weight hyperparameter and the scale_pos_weight hyperparameter by using automatic model tuning (AMT). Optimize on {"HyperParameterTuningJobObjective": {"MetricName": "validation'll", "Type": "Maximize"}}.
   • CTune all possible hyperparameters by using automatic model tuning (AMT). Optimize on {"HyperParameterTuningJobObjective": {"MetricName": "validation:f1", "Type": "Maximize"}}.
   • DTune the csv_weight hyperparameter and the scale_pos_weight hyperparameter by using automatic model tuning (AMT). Optimize on {"HyperParameterTuningJobObjective": {"MetricName": "validation:f1", "Type": "Minimize"}}.

   Show answer

   Answer: B

   Explanation

   B. Tune the csv_weight hyperparameter and the scale_pos_weight hyperparameter by using automatic model tuning (AMT). Optimize on {"HyperParameterTuningJobObjective": {"MetricName": "validation:recall", "Type": "Maximize"}}. The dataset is imbalanced, with only 5% of customers returning items (or the positive class). The goal is typically to capture as many instances of the minority class (returned items) as possible, even at the expense of some false positives. Option D might be incorrect, as the goal is to maximize the model's ability to capture instances of returned items, not minimize the F1 score.

   Source: Adapted from community discussion — F1Fan

   Next question

9. Question 239 · 368 in bank

   Select 2

   A data scientist is trying to improve the accuracy of a neural network classification model. The data scientist wants to run a large hyperparameter tuning job in Amazon SageMaker. However, previous smaller tuning jobs on the same model often ran for several weeks. The ML specialist wants to reduce the computation time required to run the tuning job. Which actions will MOST reduce the computation time for the hyperparameter tuning job? (Choose two.)

   • AUse the Hyperband tuning strategy.
   • BIncrease the number of hyperparameters.
   • CSet a lower value for the MaxNumberOfTrainingJobs parameter.
   • DUse the grid search tuning strategy.
   • ESet a lower value for the MaxParallelTrainingJobs parameter.

   Show answer

   Answer: AC

   Explanation

   Option A: Use the Hyperband tuning strategy. The Hyperband tuning strategy is a resource-efficient and time-saving approach for hyperparameter tuning. It works by running a set of hyperparameter configurations for a small number of training iterations and eliminating the poorly performing configurations early on. This strategy can significantly reduce the overall computation time compared to traditional methods like grid search or random search, especially for large hyperparameter spaces or time-consuming models like neural networks. Option E: Set a lower value for the MaxParallelTrainingJobs parameter. The MaxParallelTrainingJobs parameter in Amazon SageMaker specifies the maximum number of concurrent training jobs to be run in parallel during the hyperparameter tuning process. By setting a lower value for this parameter, the data scientist can limit the amount of computational resources used simultaneously, potentially reducing the overall computation time and cost.

   Source: Adapted from community discussion — F1Fan

   References

   • AWS documentation

   Next question

10. Question 240 · 368 in bank

    A machine learning (ML) specialist needs to solve a binary classification problem for a marketing dataset. The ML specialist must maximize the Area Under the ROC Curve (AUC) of the algorithm by training an XGBoost algorithm. The ML specialist must find values for the eta, alpha, min_child_weight, and max_depth hyperparameters that will generate the most accurate model. Which approach will meet these requirements with the LEAST operational overhead?

    • AUse a bootstrap script to install scikit-learn on an Amazon EMR cluster. Deploy the EMR cluster. Apply k-fold cross-validation methods to the algorithm.
    • BDeploy Amazon SageMaker prebuilt Docker images that have scikit-learn installed. Apply k-fold cross-validation methods to the algorithm.
    • CUse Amazon SageMaker automatic model tuning (AMT). Specify a range of values for each hyperparameter.
    • DSubscribe to an AUC algorithm that is on AWS Marketplace. Specify a range of values for each hyperparameter.

    Show answer

    Answer: C

    References

    • AWS documentation

    Next question

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

MLS-C01 practice, question 231. 368 questions available.