11. A company is using a legacy telephony platform and has several years remaining on its contract. The company wants to move to AWS and wants to implement the following machine learning features:
• Call transcription in multiple languages
• Categorization of calls based on the transcript
• Detection of the main customer issues in the calls
• Customer sentiment analysis for each line of the transcript, with positive or negative indication and scoring of that sentiment
Which AWS solution will meet these requirements with the LEAST amount of custom model training?
A. Use Amazon Transcribe to process audio calls to produce transcripts, categorize calls, and detect issues. Use Amazon Comprehend to analyze sentiment.
B. Use Amazon Transcribe to process audio calls to produce transcripts. Use Amazon Comprehend to categorize calls, detect issues, and analyze sentiment
C. Use Contact Lens for Amazon Connect to process audio calls to produce transcripts, categorize calls, detect issues, and analyze sentiment.
D. Use Contact Lens for Amazon Connect to process audio calls to produce transcripts. Use Amazon Comprehend to categorize calls, detect issues, and analyze sentiment.
Answer
C
12. A company wants to detect credit card fraud. The company has observed that an average of 2% of credit card transactions are fraudulent. A data scientist trains a classifier on a year’s worth of credit card transaction data. The classifier needs to identify the fraudulent transactions. The company wants to accurately capture as many fraudulent transactions as possible.
Which metrics should the data scientist use to optimize the classifier? (Choose two.)
A. Specificity
B. False positive rate
C. Accuracy
D. F1 score
E. True positive rate
Answer
D, E
13. A data scientist needs to develop a model to detect fraud. The data scientist has less data for fraudulent transactions than for legitimate transactions.
The data scientist needs to check for bias in the model before finalizing the model. The data scientist needs to develop the model quickly.
Which solution will meet these requirements with the LEAST operational overhead?
A. Process and reduce bias by using the synthetic minority oversampling technique (SMOTE) in Amazon EMR. Use Amazon SageMaker Studio Classic to develop the model. Use Amazon Augmented Al (Amazon A2I) to check the model for bias before finalizing the model.
B. Process and reduce bias by using the synthetic minority oversampling technique (SMOTE) in Amazon EMR. Use Amazon SageMaker Clarify to develop the model. Use Amazon Augmented AI (Amazon A2I) to check the model for bias before finalizing the model.
C. Process and reduce bias by using the synthetic minority oversampling technique (SMOTE) in Amazon SageMaker Studio. Use Amazon SageMaker JumpStart to develop the model. Use Amazon SageMaker Clarify to check the model for bias before finalizing the model.
D. Process and reduce bias by using an Amazon SageMaker Studio notebook. Use Amazon SageMaker JumpStart to develop the model. Use Amazon SageMaker Model Monitor to check the model for bias before finalizing the model.
Answer
C
14. A company maintains a 2 TB dataset that contains information about customer behaviors. The company stores the dataset in Amazon S3. The company stores a trained model container in Amazon Elastic Container Registry (Amazon ECR).
A machine learning (ML) specialist needs to score a batch model for the dataset to predict customer behavior. The ML specialist must select a scalable approach to score the model.
Which solution will meet these requirements MOST cost-effectively?
A. Score the model by using AWS Batch managed Amazon EC2 Reserved Instances. Create an Amazon EC2 instance store volume and mount it to the Reserved Instances.
B. Score the model by using AWS Batch managed Amazon EC2 Spot Instances. Create an Amazon FSx for Lustre volume and mount it to the Spot Instances.
C. Score the model by using an Amazon SageMaker notebook on Amazon EC2 Reserved Instances. Create an Amazon EBS volume and mount it to the Reserved Instances.
D. Score the model by using Amazon SageMaker notebook on Amazon EC2 Spot Instances. Create an Amazon Elastic File System (Amazon EFS) file system and mount it to the Spot Instances.
Answer
B
15. A company is building a predictive maintenance system using real-time data from devices on remote sites. There is no AWS Direct Connect connection or VPN connection between the sites and the company’s VPC. The data needs to be ingested in real time from the devices into Amazon S3.
Transformation is needed to convert the raw data into clean .csv data to be fed into the machine learning (ML) model. The transformation needs to happen during the ingestion process. When transformation fails, the records need to be stored in a specific location in Amazon S3 for human review. The raw data before transformation also needs to be stored in Amazon S3.
How should an ML specialist architect the solution to meet these requirements with the LEAST effort?
A. Use Amazon Data Firehose with Amazon S3 as the destination. Configure Firehose to invoke an AWS Lambda function for data transformation. Enable source record backup on Firehose.
B. Use Amazon Managed Streaming for Apache Kafka. Set up workers in Amazon Elastic Container Service (Amazon ECS) to move data from Kafka brokers to Amazon S3 while transforming it. Configure workers to store raw and unsuccessfully transformed data in different S3 buckets.
C. Use Amazon Data Firehose with Amazon S3 as the destination. Configure Firehose to invoke an Apache Spark job in AWS Glue for data transformation. Enable source record backup and configure the error prefix.
D. Use Amazon Kinesis Data Streams in front of Amazon Data Firehose. Use Kinesis Data Streams with AWS Lambda to store raw data in Amazon S3. Configure Firehose to invoke a Lambda function for data transformation with Amazon S3 as the destination.
Answer
A
16. A finance company has collected stock return data for 5,000 publicly traded companies. A financial analyst has a dataset that contains 2,000 attributes for each company. The financial analyst wants to use Amazon SageMaker to identify the top 15 attributes that are most valuable to predict future stock returns.
Which solution will meet these requirements with the LEAST operational overhead?
A. Use the linear leaner algorithm in SageMaker to train a linear regression model to predict the stock returns. Identify the most predictive features by ranking absolute coefficient values.
B. Use random forest regression in SageMaker to train a model to predict the stock returns. Identify the most predictive features based on Gini importance scores.
C. Use an Amazon SageMaker Data Wrangler quick model visualization to predict the stock returns. Identify the most predictive features based on the quick mode’s feature importance scores.
D. Use Amazon SageMaker Autopilot to build a regression model to predict the stock returns. Identify the most predictive features based on an Amazon SageMaker Clarify report.
Answer
D
17. A banking company provides financial products to customers around the world. A machine learning (ML) specialist collected transaction data from internal customers. The ML specialist split the dataset into training, testing, and validation datasets. The ML specialist analyzed the training dataset by using Amazon SageMaker Clarify. The analysis found that the training dataset contained fewer examples of customers in the 40 to 55 year-old age group compared to the other age groups.
Which type of pretraining bias did the ML specialist observe in the training dataset?
A. Difference in proportions of labels (DPL)
B. Class imbalance (CI)
C. Conditional demographic disparity (CDD)
D. Kolmogorov-Smirnov (KS)
Answer
B
18. A media company is building a computer vision model to analyze images that are on social media. The model consists of CNNs that the company trained by using images that the company stores in Amazon S3. The company used an Amazon SageMaker training job in File mode with a single Amazon EC2 On-Demand Instance.
Every day, the company updates the model by using about 10,000 images that the company has collected in the last 24 hours. The company configures training with only one epoch. The company wants to speed up training and lower costs without the need to make any code changes.
Which solution will meet these requirements?
A. Instead of File mode, configure the SageMaker training job to use Pipe mode. Ingest the data from a pipe.
B. Instead of File mode, configure the SageMaker training job to use FastFile mode with no other changes.
C. Instead of On-Demand Instances, configure the SageMaker training job to use Spot Instances. Make no other changes,
D. Instead of On-Demand Instances, configure the SageMaker training job to use Spot Instances, implement model checkpoints.
Answer
B
19. A machine learning (ML) specialist collected daily product usage data for a group of customers. The ML specialist appended customer metadata such as age and gender from an external data source.
The ML specialist wants to understand product usage patterns for each day of the week for customers in specific age groups. The ML specialist creates two categorical features named dayofweek and binned_age, respectively.
Which approach should the ML specialist use discover the relationship between the two new categorical features?
A. Create a scatterplot for day_of_week and binned_age.
B. Create crosstabs for day_of_week and binned_age.
C. Create word clouds for day_of_week and binned_age.
D. Create a boxplot for day_of_week and binned_age.
Answer
A
20. A company needs to develop a model that uses a machine learning (ML) model for risk analysis. An ML engineer needs to evaluate the contribution each feature of a training dataset makes to the prediction of the target variable before the ML engineer selects features.
How should the ML engineer predict the contribution of each feature?
A. Use the Amazon SageMaker Data Wrangler multicollinearity measurement features and the principal component analysis (PCA) algorithm to calculate the variance of the dataset along multiple directions in the feature space.
B. Use an Amazon SageMaker Data Wrangler quick model visualization to find feature importance scores that are between 0.5 and 1.
C. Use the Amazon SageMaker Data Wrangler bias report to identify potential biases in the data related to feature engineering.
D. Use an Amazon SageMaker Data Wrangler data flow to create and modify a data preparation pipeline. Manually add the feature scores.
Answer
B