# ADVPERF01-BP04 Evaluate AI/ML-based architecture for optimization (like contextual advertising or scaling algorithms on event context)  
<a name="advperf01-bp04"></a>

 Use AWS services to implement a low latency, high throughput inference and MLOps framework. 

## Implementation guidance
<a name="implementation-guidance-37"></a>
+  Implement low-latency, high-throughput model inference using [Amazon ECS](https://aws.amazon.com/ecs/), [Amazon EKS](https://aws.amazon.com/eks/), and [Amazon SageMaker AI](https://aws.amazon.com/sagemaker/).  
+  Implement an ML pipeline using Amazon SageMaker AI to build, train, and deploy machine learning models. Additionally, use Sage Maker for predictive scaling of compute based on learning from past event data. 

## Resources
<a name="resources-32"></a>

 **Related documentation:** 
+  [Guidance for Machine Learning for Near Real-Time Advertising on AWS](https://aws.amazon.com/solutions/guidance/machine-learning-for-near-real-time-advertising-on-aws/?did=sl_card&trk=sl_card) 
+  [Guidance for Low-Latency High-Throughput Model Inference Using Amazon ECS](https://aws.amazon.com/solutions/guidance/low-latency-high-throughput-model-inference-using-amazon-ecs/) 

 **Related videos:** 
+  [AWS re: Invent 2020: Distributed machine learning for digital video and TV ad serving](https://www.youtube.com/watch?v=u3q-P1PQig8&t=60s)