From the course: Machine Learning with SageMaker by Pearson

Unlock this course with a free trial

Join today to access over 25,200 courses taught by industry experts.

Real-time inference with SageMaker endpoints

Real-time inference with SageMaker endpoints - Amazon SageMaker Tutorial

From the course: Machine Learning with SageMaker by Pearson

Start my 1-month free trial Buy for my team

Real-time inference with SageMaker endpoints

“

Once we have our models created and deployed, we probably want to use them. So we can do real-time inference as well as batch inference. Real-time inference is where we have a question and we want an immediate answer to it. So we get an immediate prediction from our trained and deployed model. Primarily used in applications requiring low latency responses, such as fraud detection, personalization. So fraud detection, we have an example coming up in a slide. But imagine you go and you purchase a new car for $20,000 and you put it on your credit card. As that transaction comes into the bank, they are probably going to analyze it for some sort of fraud and make an immediate decision as to whether or not it appears to be fraudulent. And they are most likely doing that in an automated fashion. So machine learning model or fraud detection, probably doing real-time inference. Deploy your models to SageMaker Endpoints for real-time accessibility. We'll see this in the demo. Once we have our…

Contents