AWS Certified Machine Learning Specialty · Free Practice Question Hard
Question 17
The ML solutions team at a leading ecommerce company wants to build a real time fraud detection system. As an ML Specialist, what is the recommended course of action to build such a system with the least number of components that also ensures ease of maintenance?
-
A
Ingest the clickstream data into Kinesis Data Streams, which is then written into Kinesis Data Analytics for real time fraud detection and the processed stream data is finally directly written into EFS
-
B
Ingest the clickstream data into Kinesis Data Streams, which is then written into Kinesis Data Analytics for real time fraud detection using the Random Cut Forest Algorithm. A Lambda function sends an email alert for every fraud detected by the algorithm. The processed stream data is finally sent to Kinesis Data Firehose for subsequent storage in S3
-
C
Ingest the clickstream data into a Spark Streaming application running on EMR cluster to detect fraud records. The application then writes the data into S3
-
D
Ingest the clickstream data into Kinesis Data Analytics for real time Fraud Detection and the data is finally sent to Kinesis Data Firehose for subsequent storage in S3
Reveal correct answer
Correct answer: B
Explanation
Correct option:
Ingest the clickstream data into Kinesis Data Streams, which is then written into Kinesis Data Analytics for real time fraud detection using the Random Cut Forest Algorithm. A Lambda function sends an email alert for every fraud detected by the algorithm. The processed stream data is finally sent to Kinesis Data Firehose for subsequent storage in S3
Amazon Kinesis Data Analytics is the easiest way to analyze streaming data, gain actionable insights, and respond to your business and customer needs in real time. Amazon Kinesis Data Analytics reduces the complexity of building, managing, and integrating streaming applications with other AWS services. You can quickly build SQL queries and sophisticated Apache Flink applications in a supported language such as Java or Scala using built-in templates and operators for common processing functions to organize, transform, aggregate, and analyze data at any scale.
Using the combination of Kinesis Data Streams followed by Kinesis Data Analytics (running RCF algorithm) and then using Kinesis Data Firehose is the correct solution.
Incorrect options:
Ingest the clickstream data into Kinesis Data Analytics for real time Fraud Detection and the data is finally sent to Kinesis Data Firehose for subsequent storage in S3 - Kinesis Data Analytics cannot directly ingest incoming stream data so this option is incorrect. You can use Kinesis Data Streams to ingest the incoming stream data.
Ingest the clickstream data into Kinesis Data Streams, which is then written into Kinesis Data Analytics for real time fraud detection and the processed stream data is finally directly written into EFS - Kinesis Data Analytics cannot directly write data into EFS, so this option is incorrect.
Ingest the clickstream data into a Spark Streaming application running on EMR cluster to detect fraud records. The application then writes the data into S3 - Amazon EMR is a managed cluster platform that simplifies running big data frameworks, such as Apache Hadoop and Apache Spark, on AWS to process and analyze vast amounts of data. By using these frameworks and related open-source projects, such as Apache Hive and Apache Pig, you can process data for analytics purposes and business intelligence workloads. Using an EMR cluster would imply managing the underlying infrastructure so it’s ruled out.
Using an EMR cluster would imply managing the underlying infrastructure so this option is ruled out.
References:
https://aws.amazon.com/kinesis/data-analytics/
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
