Chapter 14: Model Deployment, Endpoints, and Operations
In the previous chapter, we learned how to build efficient and scalable recommender engines through feature engineering, natural language processing, and distributed algorithms.
In this chapter, we will tackle the next step after training a recommender engine or any machine learning model; we are going to deploy and operate the ML model. This will require us to package and register the model, build an execution runtime, build a web service, and deploy all components to an execution target.
First, we will take a look at all the required preparations to deploy ML models to production. You will learn the steps that are required in a typical deployment process, how to package and register trained models, how to define and build inferencing environments, and how to choose a deployment target to run the model.
In the next section, we will learn how to build a web service for a real-time scoring service, similar to Azure Cognitive...