Some predictive machine learning models provide interpretable results, while others are black boxes. In either case, it’s important to know how and why a model made the predictions it did. This workshop will introduce tools for interpreting machine learning models and explaining their predictions. Topics covered include:
- Inherently interpretable models (linear and logistic regression, decision trees)
- Feature importance
- Individual conditional expectation (ICE) and partial dependence (PDP) plots
- Local surrogate models (LIME)
- Shapley additive explanations (SHAP)
All methods will be discussed at an approachable, non-technical level and demonstrated using worked examples in R and Python.