MLS-C01 practice questions 21–30

1. Question 21 · 368 in bank

   An e commerce company wants to launch a new cloud-based product recommendation feature for its web application. Due to data localization regulations, any sensitive data must not leave its on-premises data center, and the product recommendation model must be trained and tested using nonsensitive data only. Data transfer to the cloud must use IPsec. The web application is hosted on premises with a PostgreSQL database that contains all the data. The company wants the data to be uploaded securely to Amazon S3 each day for model retraining. How should a machine learning specialist meet these requirements?

   • ACreate an AWS Glue job to connect to the PostgreSQL DB instance. Ingest tables without sensitive data through an AWS Site-to-Site VPN connection directly into Amazon S3.
   • BCreate an AWS Glue job to connect to the PostgreSQL DB instance. Ingest all data through an AWS Site-to-Site VPN connection into Amazon S3 while removing sensitive data using a PySpark job.
   • CUse AWS Database Migration Service (AWS DMS) with table mapping to select PostgreSQL tables with no sensitive data through an SSL connection. Replicate data directly into Amazon S3.
   • DUse PostgreSQL logical replication to replicate all data to PostgreSQL in Amazon EC2 through AWS Direct Connect with a VPN connection. Use AWS Glue to move data from Amazon EC2 to Amazon S3.

   Show answer

   Answer: A

   Explanation

   ASK : Extract Data over IPsec So we need an ETL + Site to site VPN GLUE is an ETL service but can it connect to PostgreSQL? yes https://docs.aws.amazon.com/glue/latest/dg/aws-glue-programming-etl-connect.html#aws-glue-programming-etl-connect-jdbc How to connect Glue to an on-site DB https://aws.amazon.com/blogs/big-data/how-to-access-and-analyze-on-premises-data-stores-using-aws-glue/ My Answer would be A Anser C only makes a 443 (SSL) connection so does not meet the IPsec requirement

   Source: Adapted from community discussion — cnethers

   References

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

   Next question

2. Question 22 · 368 in bank

   Select 2

   A logistics company needs a forecast model to predict next month's inventory requirements for a single item in 10 warehouses. A machine learning specialist uses Amazon Forecast to develop a forecast model from 3 years of monthly data. There is no missing data. The specialist selects the DeepAR+ algorithm to train a predictor. The predictor means absolute percentage error (MAPE) is much larger than the MAPE produced by the current human forecasters. Which changes to the CreatePredictor API call could improve the MAPE? (Choose two.)

   • ASet PerformAutoML to true.
   • BSet ForecastHorizon to 4.
   • CSet ForecastFrequency to W for weekly.
   • DSet PerformHPO to true.
   • ESet FeaturizationMethodName to filling.

   Show answer

   Answer: AD

   Explanation

   I would choose A and D, however both of them is not possible at the same time. The question is ambiguous, it could mean which two options, but no necessarily both. A - If you want Amazon Forecast to evaluate each algorithm and choose the one that minimizes the objective function, set PerformAutoML to true. D - The following algorithms support HPO: - > DeepAR+.

   Source: Adapted from community discussion — scuzzy2010

   References

   • AWS documentation

   Next question

3. Question 23 · 368 in bank

   A data scientist wants to use Amazon Forecast to build a forecasting model for inventory demand for a retail company. The company has provided a dataset of historic inventory demand for its products as a .csv file stored in an Amazon S3 bucket. The table below shows a sample of the dataset.

   

   How should the data scientist transform the data?

   • AUse ETL jobs in AWS Glue to separate the dataset into a target time series dataset and an item metadata dataset. Upload both datasets as .csv files to Amazon S3.
   • BUse a Jupyter notebook in Amazon SageMaker to separate the dataset into a related time series dataset and an item metadata dataset. Upload both datasets as tables in Amazon Aurora.
   • CUse AWS Batch jobs to separate the dataset into a target time series dataset, a related time series dataset, and an item metadata dataset. Upload them directly to Forecast from a local machine.
   • DUse a Jupyter notebook in Amazon SageMaker to transform the data into the optimized protobuf recordIO format. Upload the dataset in this format to Amazon S3.

   Show answer

   Answer: A

   Explanation

   I would answer A. Target and metadata must be in two files and loaded from S3, based on documentation: https://docs.aws.amazon.com/forecast/latest/dg/dataset-import-guidelines-troubleshooting.html

   Source: Adapted from community discussion — [Removed]

   References

   • AWS documentation
   • AWS documentation

   Next question

4. Question 24 · 368 in bank

   A Machine Learning Specialist is working with a large company to leverage machine learning within its products. The company wants to group its customers into categories based on which customers will and will not churn within the next 6 months. The company has labeled the data available to the Specialist. Which machine learning model type should the Specialist use to accomplish this task?

   • ALinear regression
   • BClassification
   • CClustering
   • DReinforcement learning

   Show answer

   Answer: B

   Explanation

   CLASSIFICATION - Binary Classification - Supervised Learning to be precise The company wants to predict customer churn (whether a customer will leave or stay). The data is labeled, meaning we have historical outcomes (churn or no churn). The task involves categorizing customers into two groups: Customers who will churn (leave) Customers who will not churn (stay) This means the problem is a Supervised Learning problem, specifically a binary classification problem. The company wants to predict customer churn (whether a customer will leave or stay). The data is labeled, meaning we have historical outcomes (churn or no churn). The task involves categorizing customers into two groups: Customers who will churn (leave) Customers who will not churn (stay) This means the problem is a Supervised Learning problem, specifically a binary classification problem.

   Source: Adapted from community discussion — JonSno

   Next question

5. Question 25 · 368 in bank

   A machine learning specialist is running an Amazon SageMaker endpoint using the built-in object detection algorithm on a P3 instance for real-time predictions in a company's production application. When evaluating the model's resource utilization, the specialist notices that the model is using only a fraction of the GPU. Which architecture changes would ensure that provisioned resources are being utilized effectively?

   • ARedeploy the model as a batch transform job on an M5 instance.
   • BRedeploy the model on an M5 instance. Attach Amazon Elastic Inference to the instance.
   • CRedeploy the model on a P3dn instance.
   • DDeploy the model onto an Amazon Elastic Container Service (Amazon ECS) cluster using a P3 instance.

   Show answer

   Answer: B

   Explanation

   Amazon Elastic Inference allows you to attach low-cost GPU-powered acceleration to EC2 and Sagemaker instances, to reduce the cost of running deep learning inference. You can choose any CPU instance that is best suited to the overall compute and memory needs of your application, and then separately configure the right amount of GPU-powered inference acceleration. This would allow you to efficiently utilize resources and reduce costs.

   Source: Adapted from community discussion — AjoseO

   References

   • AWS documentation

   Next question

6. Question 26 · 368 in bank

   A data scientist uses an Amazon SageMaker notebook instance to conduct data exploration and analysis. This requires certain Python packages that are not natively available on Amazon SageMaker to be installed on the notebook instance. How can a machine learning specialist ensure that required packages are automatically available on the notebook instance for the data scientist to use?

   • AInstall AWS Systems Manager Agent on the underlying Amazon EC2 instance and use Systems Manager Automation to execute the package installation commands.
   • BCreate a Jupyter notebook file (.ipynb) with cells containing the package installation commands to execute and place the file under the /etc/init directory of each Amazon SageMaker notebook instance.
   • CUse the conda package manager from within the Jupyter notebook console to apply the necessary conda packages to the default kernel of the notebook.
   • DCreate an Amazon SageMaker lifecycle configuration with package installation commands and assign the lifecycle configuration to the notebook instance.

   Show answer

   Answer: D

   Explanation

   You can install packages using the following methods: 1-Lifecycle configuration scripts 2-Notebooks – The following commands are supported. %conda install %pip install 3-The Jupyter terminal – You can install packages using pip and conda directly.

   Source: Adapted from community discussion — mona_mansour

   References

   • AWS documentation

   Next question

7. Question 27 · 368 in bank

   A data scientist needs to identify fraudulent user accounts for a company's ecommerce platform. The company wants the ability to determine if a newly created account is associated with a previously known fraudulent user. The data scientist is using AWS Glue to cleanse the company's application logs during ingestion. Which strategy will allow the data scientist to identify fraudulent accounts?

   • AExecute the built-in FindDuplicates Amazon Athena query.
   • BCreate a FindMatches machine learning transform in AWS Glue.
   • CCreate an AWS Glue crawler to infer duplicate accounts in the source data.
   • DSearch for duplicate accounts in the AWS Glue Data Catalog.

   Show answer

   Answer: B

   Explanation

   B ,You can use the FindMatches transform to find duplicate records in the source data. A labeling file is generated or provided to help teach the transform.

   Source: Adapted from community discussion — mona_mansour

   References

   • AWS documentation

   Next question

8. Question 28 · 368 in bank

   Select 2

   A Data Scientist is developing a machine learning model to classify whether a financial transaction is fraudulent. The labeled data available for training consists of 100,000 non-fraudulent observations and 1,000 fraudulent observations. The Data Scientist applies the XGBoost algorithm to the data, resulting in the following confusion matrix when the trained model is applied to a previously unseen validation dataset. The accuracy of the model is 99.1%, but the Data Scientist needs to reduce the number of false negatives.

   

   Which combination of steps should the Data Scientist take to reduce the number of false negative predictions by the model? (Choose two.)

   • AChange the XGBoost eval_metric parameter to optimize based on Root Mean Square Error (RMSE).
   • BIncrease the XGBoost scale_pos_weight parameter to adjust the balance of positive and negative weights.
   • CIncrease the XGBoost max_depth parameter because the model is currently underfitting the data.
   • DChange the XGBoost eval_metric parameter to optimize based on Area Under the ROC Curve (AUC).
   • EDecrease the XGBoost max_depth parameter because the model is currently overfitting the data.

   Show answer

   Answer: BD

   Explanation

   Step B: Increasing the XGBoost scale_pos_weight parameter to adjust the balance of positive and negative weights can help the model deal with the imbalanced dataset. According to the XGBoost documentation, this parameter controls the balance of positive and negative weights, and is useful for unbalanced classes. A typical value to consider is sum(negative instances) / sum(positive instances). In this case, since there are 100 times more non-fraudulent transactions than fraudulent ones, setting scale_pos_weight to 100 can make the model more sensitive to the minority class and reduce false negatives. Step D: Changing the XGBoost eval_metric parameter to optimize based on Area Under the ROC Curve (AUC) can help the model focus on improving the true positive rate and the true negative rate, which are both important for fraud detection. According to the XGBoost

   Source: Adapted from community discussion — Mickey321

   References

   • AWS documentation

   Next question

9. Question 29 · 368 in bank

   A data scientist has developed a machine learning translation model for English to Japanese by using Amazon SageMaker's built-in seq2seq algorithm with 500,000 aligned sentence pairs. While testing with sample sentences, the data scientist finds that the translation quality is reasonable for an example as short as five words. However, the quality becomes unacceptable if the sentence is 100 words long. Which action will resolve the problem?

   • AChange preprocessing to use n-grams.
   • BAdd more nodes to the recurrent neural network (RNN) than the largest sentence's word count.
   • CAdjust hyperparameters related to the attention mechanism.
   • DChoose a different weight initialization type.

   Show answer

   Answer: C

   Explanation

   I agree with an answer of C Attention mechanism. The disadvantage of an encoder-decoder framework is that model performance decreases as and when the length of the source sequence increases because of the limit of how much information the fixed-length encoded feature vector can contain. To tackle this problem, in 2015, Bahdanau et al. proposed the attention mechanism. In an attention mechanism, the decoder tries to find the location in the encoder sequence where the most important information could be located and uses that information and previously decoded words to predict the next token in the sequence.

   Source: Adapted from community discussion — cnethers

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

10. Question 30 · 368 in bank

    Select 2

    A financial company is trying to detect credit card fraud. The company observed that, on average, 2% of credit card transactions were fraudulent. A data scientist trained a classifier on a year's worth of credit card transactions data. The model needs to identify the fraudulent transactions (positives) from the regular ones (negatives). The company's goal is to accurately capture as many positives as possible. Which metrics should the data scientist use to optimize the model? (Choose two.)

    • ASpecificity
    • BFalse positive rate
    • CAccuracy
    • DArea under the precision-recall curve
    • ETrue positive rate

    Show answer

    Answer: DE

    Explanation

    This is incorrect. The goal is to capture as many positive as possible, so false positive is not a concern. suppose we have 100 samples, 2 are positive, the rest 98 negative. We have two models: A has TP = 2, TN = 48, FP = 50, FN = 0. B has TP = 1, TN = 88, FP = 10, FN = 1. Model A has higher false positive rate (50/98 vs 10/98). However we will choose A, since it captures all TP. I will go with D, E.

    Source: Adapted from community discussion — seanLu

    Next question

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

MLS-C01 practice, question 21. 368 questions available.