12. Productionizing Your AI Applications
Overview
In this chapter, we’ll tie a lot of things together that we have covered in the book. The end goal of an AI application should always be to bring business value. That means all the great models that are created by data scientists should be put into production. It’s quite difficult to productionize and maintain an application that contains one or more machine learning models. In this chapter, we’ll discuss three major options for productionizing an AI application, so you’ll be well equipped to pick a method for your situation.
By the end of this chapter, you will be able to describe the steps it takes to run a machine learning model in production, list a few common options to run models in production, and design and implement a continuous delivery pipeline for models.
