Chapter 10: Monitoring ML Models in Production with SageMaker Model Monitor
Having a model put into production for inferencing isn't the end of the machine learning (ML) life cycle. It is just the beginning of an important topic: how do we make sure the model is performing as it is designed to and as expected in real life? Monitoring how the model performs in production, especially on data that the model has never seen before, is made easy with SageMaker Studio. You will learn how to set up model monitoring for models deployed in SageMaker, detect data drift and performance drift, and visualize results in SageMaker Studio, so that you can let the system detect the degradation of your ML model automatically.
In this chapter, we will be learning about the following:
- Understanding drift in ML
- Monitoring data and model performance drift in SageMaker Studio
- Reviewing model monitoring results in SageMaker Studio
