Inglis, Alan and Parnell, Andrew and Hurley, Catherine B. (2022) Visualizing Variable Importance and Variable Interaction Effects in Machine Learning Models. Journal of Computational and Graphical Statistics. pp. 1-13. ISSN 1061-8600

Preview

Download (4MB) | Preview

Abstract

Variable importance, interaction measures, and partial dependence plots are important summaries in the interpretation of statistical and machine learning models. In this article, we describe new visualization techniques for exploring these model summaries. We construct heatmap and graph-based displays showing variable importance and interaction jointly, which are carefully designed to highlight important aspects of the fit. We describe a new matrix-type layout showing all single and bivariate partial dependence plots, and an alternative layout based on graph Eulerians focusing on key subsets. Our new visualizations are model-agnostic and are applicable to regression and classification supervised learning settings. They enhance interpretation even in situations where the number of variables is large. Our R package vivid (variable importance and variable interaction displays) provides an implementation. Supplementary files for this article are available online.

Item Type:	Article
Keywords:	Black-box; Model explanation; Model visualization;
Academic Unit:	Faculty of Science and Engineering > Mathematics and Statistics Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	15495
Identification Number:	https://doi.org/10.1080/10618600.2021.2007935
Depositing User:	Andrew Parnell
Date Deposited:	15 Feb 2022 12:12
Journal or Publication Title:	Journal of Computational and Graphical Statistics
Publisher:	American Statistical Association
Refereed:	Yes
URI:	Publisher
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads