Chapter 16 Interpretable Machine Learning

Learning objectives:

1. Understand the importance of interpretability in machine learning models.
2. Learn about global and local interpretation.
3. Understand the trade-off between interpretation and performance.
4. Learn about model-specific and model-agnostic methods.
5. Understand the concept of permutation-based feature importance.
6. Understand the concept of partial dependence.
7. Learn about Individual Conditional Expectation (ICE).
8. Explain different methods to find interactions.
9. Explain the main features for local observations.