Interpretability and Explainability in Machine Learning Modeling
The majority of the machine learning models we use or develop are complex and require the use of explainability techniques to identify opportunities for improving their performance, reducing their bias, and increasing their reliability.
We will look at the following topics in this chapter:
- Interpretable versus black-box machine learning
- Explainability methods in machine learning
- Practicing machine learning explainability in Python
- Reviewing why having explainability is not enough
By the end of this chapter, you will have learned about the importance of explainability in machine learning modeling and practiced using some of the explainability techniques in Python.
