Interpretable Machine Learning

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 importanceIndividual conditional expectation (ICE) and partial dependence (PDP) plotsLocal 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. Register Now