Bringing a Ruler Into the Black Box: Uncovering Feature Impact from Individual Conditional Expectation Plots

TL;DR

This paper introduces ICE feature impact, a novel, model-agnostic metric derived from ICE plots that helps interpret feature influence on model predictions, including in-distribution analysis and heterogeneity measures.

Contribution

The paper extends ICE plots with a new feature impact metric, providing a more interpretable and versatile tool for understanding feature effects in machine learning models.

Findings

ICE feature impact correlates well with feature importance.

In-distribution ICE impact reduces out-of-distribution bias.

Heterogeneity measures reveal feature effect variability.

Abstract

As machine learning systems become more ubiquitous, methods for understanding and interpreting these models become increasingly important. In particular, practitioners are often interested both in what features the model relies on and how the model relies on them--the feature's impact on model predictions. Prior work on feature impact including partial dependence plots (PDPs) and Individual Conditional Expectation (ICE) plots has focused on a visual interpretation of feature impact. We propose a natural extension to ICE plots with ICE feature impact, a model-agnostic, performance-agnostic feature impact metric drawn out from ICE plots that can be interpreted as a close analogy to linear regression coefficients. Additionally, we introduce an in-distribution variant of ICE feature impact to vary the influence of out-of-distribution points as well as heterogeneity and non-linearity measures to characterize feature impact. Lastly, we demonstrate ICE feature impact's utility in several tasks using real-world data.