Debugging Machine Learning Models with Python

11

Avoiding and Detecting Data and Concept Drifts

We talked about the effect of data and concept drifts in machine learning modeling in Chapter 9, Testing and Debugging for Production. In this chapter, we want to go deeper into these concepts and practice detecting drifts in Python.

Here, you will learn about the importance of concepts we introduced earlier, such as model versioning and model monitoring, to avoid drifts and practice with some of the Python libraries for drift detection.

In this chapter, we will cover the following topics:

• Avoiding drifts in your models
• Detecting drifts

By the end of this chapter, you will be able to detect drifts in your machine learning models in Python and have reliable models in production.

Technical requirements ...