Given these varying requirements, which deployment target is the MOST SUITABLE for each model?

You are a machine learning engineer at a fintech company that has developed several models for various use cases, including fraud detection, credit scoring, and personalized marketing. Each model has different performance and deployment requirements. The fraud detection model requires real-time predictions with low latency and needs to scale quickly based on incoming transaction volumes. The credit scoring model is computationally intensive but can tolerate batch processing with slightly higher latency. The personalized marketing model needs to be triggered by events and doesn’t require constant availability.

Given these varying requirements, which deployment target is the MOST SUITABLE for each model?
A . Deploy the fraud detection model using AWS Lambda for serverless, on-demand execution, deploy the credit scoring model on Amazon EKS for scalable batch processing, and deploy the personalized marketing model on SageMaker endpoints to handle event-driven inference
B . Deploy the fraud detection model using SageMaker endpoints for low-latency, real-time predictions, deploy the credit scoring model on Amazon ECS for batch processing, and deploy the personalized marketing model using AWS Lambda for event-driven execution
C . Deploy all three models on a single Amazon EKS cluster to take advantage of Kubernetes orchestration, ensuring consistent management and scaling across different use cases
D . Deploy the fraud detection model on Amazon ECS for auto-scaling based on demand, deploy the credit scoring model using SageMaker endpoints for real-time scoring, and deploy the personalized marketing model on Amazon EKS for event-driven processing

View Answer

Answer: B

Explanation:

Correct option:

Deploy the fraud detection model using SageMaker endpoints for low-latency, real-time predictions, deploy the credit scoring model on Amazon ECS for batch processing, and deploy the personalized marketing model using AWS Lambda for event-driven execution

Real-time inference is ideal for inference workloads where you have real-time, interactive, low latency requirements. You can deploy your model to SageMaker hosting services and get an endpoint that can be used for inference. These endpoints are fully managed and support autoscaling. SageMaker endpoints are optimized for low-latency, real-time predictions, making them ideal for the fraud detection model.

Amazon ECS provides a service scheduler for long-running tasks and applications. It also provides the ability to run standalone tasks or scheduled tasks for batch jobs or single run tasks. You can specify the task placement strategies and constraints for running tasks that best meet your needs. Amazon ECS is well-suited for batch processing tasks, making it a good choice for the credit scoring model.

AWS Lambda is ideal for the event-driven nature of the personalized marketing model, allowing it to scale on-demand with minimal cost.

via – https://docs.aws.amazon.com/AmazonECS/latest/developerguide/scheduling_tasks.html

Incorrect options:

Deploy the fraud detection model using AWS Lambda for serverless, on-demand execution, deploy the credit scoring model on Amazon EKS for scalable batch processing, and deploy the personalized marketing model on SageMaker endpoints to handle event-driven inference – AWS Lambda is serverless and ideal for event-driven tasks, but it may not provide the low-latency, real-time performance required for fraud detection. SageMaker endpoints are better suited for this use case. The credit scoring model is better suited for ECS, where batch processing can be efficiently managed, while personalized marketing is a good fit for AWS Lambda.

Deploy all three models on a single Amazon EKS cluster to take advantage of Kubernetes orchestration, ensuring consistent management and scaling across different use cases – Deploying all models on a

single Amazon EKS cluster could be overkill and lead to unnecessary complexity. While Kubernetes provides powerful orchestration, it might be excessive for simple, event-driven or batch workloads.

Deploy the fraud detection model on Amazon ECS for auto-scaling based on demand, deploy the credit scoring model using SageMaker endpoints for real-time scoring, and deploy the personalized marketing model on Amazon EKS for event-driven processing – While Amazon ECS can handle auto-scaling, it is not as optimized for real-time, low-latency predictions as SageMaker endpoints. Additionally, using SageMaker endpoints for the credit scoring model does not align well with batch processing needs. The personalized marketing model is better suited to AWS Lambda rather than Amazon EKS, which is more complex and designed for containerized applications with continuous workloads.

References:

https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints.html

https://docs.aws.amazon.com/AmazonECS/latest/developerguide/scheduling_tasks.html