https://medium.com/@julsimon/mastering-the-mystical-art-of-model-deployment-c0cafe011175

With all the talk about algorithm selection, hyper parameter optimization and so on, you could think that training models is the hardest part of the Machine Learning process. However, in my experience, the really tricky step is to deploy these models safely in a web production environment.

In this post, I’ll first talk about the typical tasks required to deploy and validate models in production. Then, I’ll present several model deployment techniques and how to implement them with Amazon SageMaker. In particular, I’ll show you in detail how to host multiple models on the same prediction endpoint, an important technique to minimize deployment risks.