Visualizing the Feature Importance for Black Box Models

TL;DR

This paper introduces local feature importance methods and visualization tools like PI and ICI plots to interpret black box models, along with a fair Shapley importance measure for model comparison.

Contribution

It proposes new local importance visualization tools and a Shapley-based importance measure, enhancing interpretability and comparison of machine learning models.

Findings

PI and ICI plots visualize feature effects on model performance.

Averaging ICI curves yields the PI curve, linking local and global importance.

Shapley importance fairly distributes model performance among features.

Abstract

In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations. Our proposed methods are related to partial dependence (PD) and individual conditional expectation (ICE) plots, but visualize the expected (conditional) feature importance instead of the expected (conditional) prediction. Furthermore, we show that averaging ICI curves across observations yields a PI curve, and integrating the PI curve with respect to the distribution of the considered feature results in the global feature importance. Another contribution of our paper is the Shapley feature importance, which fairly distributes the overall performance of a model among the features according to the marginal contributions and which can be used to compare the feature importance across different models.