From the course: Learning Amazon SageMaker AI

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

Generating predictions

Generating predictions

- [Narrator] Have you ever wished you could predict the future? Well, now you can, at least when it comes to traffic in Dataville. Your model has been trained and deployed, and now, it's time to let it do its magic. Think of your model as a crystal ball. You feed it data, and it tells you what's coming next. Traffic congestion, clear roads, your model knows it all. Real-time inference allows you to send live data to your deployed model, and instantly get predictions in return. This is especially useful when you need immediate decisions, like predicting traffic congestion based on current road conditions. Once your model is deployed on an endpoint, you can send data to the endpoint through an API call, and the model will process the data and return a prediction within seconds. For example, in Dataville, you'll send traffic data like vehicle count, average speed, and weather conditions, and the model will predict whether traffic will be light, moderate, or heavy. Now, let's walk through…

Contents