Deploying ML Models for Real-Time Inferencing

In this chapter, we will look at how data scientists and ML professionals can make predictions available through a REST service hosted in Azure to support real-time predictions. Data is sent to a REST API, and the predicted result is provided in the response. This allows for a variety of applications to consume and leverage a model created with AMLS. We will explore a variety of options for making your models available in real time with AML.

So far, we have leveraged AMLS to handle feature engineering and built and registered models. In this chapter, we will focus on providing solutions that leverage your model to provide predictions on datasets in real time.

Azure Machine Learning provides several options for providing inferencing to business users to support batch and real-time inferencing use cases.

In this chapter, we will cover the following topics:

• Understanding real-time inferencing and batch scoring
• Deploying...