AWS Certified AI PractitionerAWS Services for AI/ML and Generative AIMedium
A financial institution is developing a fraud detection system. They need to analyze vast amounts of transaction data, identify anomalous patterns that may indicate fraudulent activity, and continuously improve their detection models. Due to the sensitive nature of the data, all data processing and model training must occur within a private network and not traverse the public internet. Which combination of AWS services should they use to achieve this securely and efficiently?
- AAmazon Kinesis Data Firehose, AWS Lambda, Amazon S3
- BAmazon QuickSight, AWS Glue, Amazon DynamoDB
- CAmazon Comprehend, Amazon Transcribe, AWS WAF
- DAmazon SageMaker, Amazon VPC, AWS PrivateLink
Show answer & explanationAnswer & explanation
Correct answer: D. Amazon SageMaker, Amazon VPC, AWS PrivateLink
Amazon SageMaker provides the tools for building, training, and deploying ML models for fraud detection. Amazon VPC allows for isolated network environments, and AWS PrivateLink ensures that connections to SageMaker (and other AWS services) remain within the AWS network, without exposing data to the public internet, satisfying the security requirements.
Why the other options are wrong
- A. These services are for data ingestion, serverless computing, and object storage, respectively. While useful, they don't directly address the ML model training/deployment or the private network connectivity requirement for ML services.
- B. These services are for business intelligence, ETL, and NoSQL databases, which are not the primary tools for building and deploying ML models for fraud detection, nor do they directly address private network connectivity for ML services.
- C. These are NLP and speech-to-text services, combined with a web application firewall, which are unrelated to building a fraud detection ML model on private networks.
AWS PrivateLink
A networking service that provides private connectivity between VPCs and AWS services, or between VPCs and on-premises networks, without exposing data to the public internet.
- Uses interface VPC endpoints.
- Traffic remains within the Amazon network.
- Enhances security and compliance for sensitive data.
Memory trick: SageMaker's VPC Link keeps fraud models safe.