Accumulated Local Effect Plots (ALEs) | Explanation & Python Code

Highly correlated features can wreak havoc on your machine-learning model interpretations. To overcome this, we could rely on good feature selection. But there are still cases when a feature, although highly correlated, will provide some unique information leading to a more accurate model. So we need a method that can provide clear interpretations, even with multicollinearity. Thankfully we can rely on ALEs. We give you the intuition for how ALEs are created, formally define the algorithm used to create ALEs and apply ALEs using Python and the Alibi Explain package. We will see that, unlike other XAI methods like SHAP, LIME, ICE Plots and Friedman's H-stat, ALEs give interpretations that are robust to multicollinearity. 🚀 Free Course 🚀 Signup here: https://mailchi.mp/40909011987b/signup XAI course: https://adataodyssey.com/courses/xai-with-python/ SHAP course: https://adataodyssey.com/courses/shap-with-python/ 🚀 Companion article with link to code (no-paywall link): 🚀 https://medium.com/data-science/deep-dive-on-accumulated-local-effect-plots-ales-with-python-0fc9698ed0ee?sk=e8e9ccb23edf2ad33dc60b1e16cf2751 🚀 Useful playlists 🚀 https://www.youtube.com/playlist?list=PLqDyyww9y-1SwNZ-6CmvfXDAOdLS7yUQ4 https://www.youtube.com/playlist?list=PLqDyyww9y-1SJgMw92x90qPYpHgahDLIK https://www.youtube.com/playlist?list=PLqDyyww9y-1Q0zWbng6vUOG1p3oReE2xS 🚀 Get in touch 🚀 Medium: https://conorosullyds.medium.com/ Threads: https://www.threads.net/@conorosullyds Twitter: https://twitter.com/conorosullyDS Website: https://adataodyssey.com/ 🚀 Chapters 🚀 00:00 Introduction 01:17 Intuition 04:39 Formal Algorithm 07:22 Python Code