A web retail company wants to implement a near-real-time clickstream analytics solution. The company wants to analyze the data with an open-source package. The analytics application will process the…

Question

Options

• AUse Amazon Kinesis Data Streams to collect the data. Use Amazon EMR with Apache Flink to
• BUse Amazon Kinesis Data Streams to collect the data. Use Amazon Kinesis Data Analytics with Apache
• CUse Amazon Managed Streaming for Apache Kafka (Amazon MSK) to collect the data. Use Amazon
• DUse Amazon Kinesis Data Streams to collect the data. Use Amazon EMR with Apache Flink to

• A
  15% (3)
• B
  70% (14)
• C
  10% (2)
• D
  5% (1)

Explanation

The requirements are: near-real-time processing, open-source analytics package, raw data accessible for up to 1 year, and minimal operational overhead. Option B uses Kinesis Data Streams (which supports extended data retention up to 365 days, satisfying the 1-year raw data requirement) and Amazon Kinesis Data Analytics with Apache Flink (a fully managed, serverless service for running Apache Flink - an open-source stream processing framework). Because Kinesis Data Analytics is fully managed, it requires the least operational effort. Options A and D use EMR with Apache Flink, which requires provisioning and managing an EMR cluster - more operational overhead. Option C uses Amazon MSK (managed Kafka), which has higher operational complexity and cost compared to Kinesis for this use case.

No community discussion yet for this question.