Summary
In this chapter, you learned about interpretable machine learning models and how explainability techniques could help you in improving the performance and reliability of your models. You learned about different local and global explainability techniques, such as SHAP and LIME, and practiced with them in Python. You also had the chance to practice with the provided Python code to learn how to use machine learning explainability techniques in your projects.
In the next chapter, you will learn about the approaches to detect and decrease biases in your models and how you can use the available functionalities in Python to meet the necessary fairness criteria when developing machine learning models.
