AWS Certified Machine Learning Engineer Associate · Free Practice Question Medium
Question 6
A manufacturing company is building an anomaly detection system to identify defective products in its production lines. The datasets include sensor logs from IoT devices stored in Amazon S3 and a list of production metadata from an on-premises SQL database.
The company must:
Aggregate and preprocess the data from multiple sources.
Implement a solution to detect anomalies automatically in the sensor data.
Visualize the results for analysis by the operations team.
Which solution will meet these requirements most efficiently?
-
A
Use Amazon SageMaker Data Wrangler to aggregate, clean, and prepare data for anomaly detection while generating visual insights
-
B
Use Amazon EMR with Spark MLlib to run anomaly detection algorithms and visualize the results using custom dashboards
-
C
Use Amazon Athena to query the sensor data and identify anomalies through SQL queries. Use Amazon QuickSight to visualize the results
-
D
Use Amazon Kinesis Data Streams to process and analyze the sensor data in real time for anomaly detection. Use Amazon QuickSight to visualize the results
Reveal correct answer
Correct answer: A
Explanation
Correct option:
Use Amazon SageMaker Data Wrangler to aggregate, clean, and prepare data for anomaly detection while generating visual insights
Amazon SageMaker Data Wrangler is a managed service designed to simplify data aggregation, cleaning, and feature engineering for machine learning workflows. It connects seamlessly to data sources like Amazon S3 and SQL databases, allowing engineers to preprocess large datasets and detect anomalies efficiently. It also provides built-in visualizations for analyzing trends, correlations, and outliers.
Key Benefits:
Integrates with Amazon S3 and on-premises databases for data aggregation.
Provides built-in anomaly detection tools and visual insights for streamlined analysis.
Simplifies feature engineering and model input preparation.
SageMaker Data Wrangler:
Incorrect options:
Use Amazon Kinesis Data Streams to process and analyze the sensor data in real time for anomaly detection. Use Amazon QuickSight to visualize the results - Amazon Kinesis Data Streams is designed for real-time data ingestion and streaming. While it can process large volumes of sensor data in real time, it does not include built-in anomaly detection capabilities or support data aggregation and preprocessing for machine learning workflows. Additional services like Amazon SageMaker or custom code would be required to analyze anomalies, thereby increasing complexity for the solution.
Use Amazon Athena to query the sensor data and identify anomalies through SQL queries. Use Amazon QuickSight to visualize the results - Athena is a query service that allows running SQL queries directly on Amazon S3 data. While useful for ad hoc analysis, it does not support automatic anomaly detection or data preprocessing, making it less suitable for this use case.
Use Amazon EMR with Spark MLlib to run anomaly detection algorithms and visualize the results using custom dashboards - While EMR with Spark MLlib is powerful for anomaly detection, it requires significant manual configuration, coding, and operational overhead. Custom dashboards for visualization further add complexity compared to SageMaker Data Wrangler.
References:
https://docs.aws.amazon.com/sagemaker/latest/dg/data-wrangler.html
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
