2 papers
stat.ME2025
Measuring Variable Importance via Accumulated Local Effects
Jingyu Zhu, Daniel W. Apley
A shortcoming of black-box supervised learning models is their lack of interpretability or transparency. To facilitate interpretation, post-hoc global variable importance measures…
stat.ME2016
Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models
Daniel W. Apley, Jingyu Zhu
When fitting black box supervised learning models (e.g., complex trees, neural networks, boosted trees, random forests, nearest neighbors, local kernel-weighted methods, etc.), vis…