MLS-C01 · Question #29
A Machine Learning Specialist is working with a large cybersecurity company that manages security events in real time for companies around the world. The cybersecurity company wants to design a…
The correct answer is A. Ingest the data using Amazon Kinesis Data Firehose, and use Amazon Kinesis Data Analytics. Amazon Kinesis Data Firehose is purpose-built for real-time data ingestion at scale, and Amazon Kinesis Data Analytics supports running machine learning algorithms (like Random Cut Forest for anomaly detection) directly on streaming data as it arrives. Critically, Firehose can…
Question
A Machine Learning Specialist is working with a large cybersecurity company that manages security events in real time for companies around the world. The cybersecurity company wants to design a solution that will allow it to use machine learning to score malicious events as anomalies on the data as it is being ingested. The company also wants be able to save the results in its data lake for later processing and analysis. What is the MOST efficient way to accomplish these tasks?
Options
- AIngest the data using Amazon Kinesis Data Firehose, and use Amazon Kinesis Data Analytics
- BIngest the data into Apache Spark Streaming using Amazon EMR, and use Spark MLlib with k-
- CIngest the data and store it in Amazon S3. Use AWS Batch along with the AWS Deep Learning
- DIngest the data and store it in Amazon S3. Have an AWS Glue job that is triggered on demand
How the community answered
(16 responses)- A81% (13)
- B13% (2)
- D6% (1)
Explanation
Amazon Kinesis Data Firehose is purpose-built for real-time data ingestion at scale, and Amazon Kinesis Data Analytics supports running machine learning algorithms (like Random Cut Forest for anomaly detection) directly on streaming data as it arrives. Critically, Firehose can simultaneously deliver the raw data to Amazon S3, fulfilling the data lake requirement without a separate pipeline. Options C and D both require writing to S3 first and then triggering a separate batch process, which introduces latency and violates the 'as it is being ingested' real-time requirement. Option B (EMR with Spark MLlib) can handle streaming but is far more complex to set up and operate than the managed Kinesis stack, making it less efficient for this use case.
Topics
Community Discussion
No community discussion yet for this question.