Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates

TL;DR

This paper introduces a novel fair feature importance score for tree-based models, enabling interpretation of how features contribute to fairness or bias in complex ML systems, with validation on simulations and real datasets.

Contribution

The paper proposes a new fair feature importance score for trees that directly interprets feature contributions to fairness, addressing a gap in existing interpretability methods.

Findings

The score effectively identifies biased features in tree models.

Validation shows the score provides meaningful fairness interpretations.

Applicable to both ensemble and surrogate tree models.

Abstract

Across various sectors such as healthcare, criminal justice, national security, finance, and technology, large-scale machine learning (ML) and artificial intelligence (AI) systems are being deployed to make critical data-driven decisions. Many have asked if we can and should trust these ML systems to be making these decisions. Two critical components are prerequisites for trust in ML systems: interpretability, or the ability to understand why the ML system makes the decisions it does, and fairness, which ensures that ML systems do not exhibit bias against certain individuals or groups. Both interpretability and fairness are important and have separately received abundant attention in the ML literature, but so far, there have been very few methods developed to directly interpret models with regard to their fairness. In this paper, we focus on arguably the most popular type of ML interpretation: feature importance scores. Inspired by the use of decision trees in knowledge distillation, we propose to leverage trees as interpretable surrogates for complex black-box ML models. Specifically, we develop a novel fair feature importance score for trees that can be used to interpret how each feature contributes to fairness or bias in trees, tree-based ensembles, or tree-based surrogates of any complex ML system. Like the popular mean decrease in impurity for trees, our Fair Feature Importance Score is defined based on the mean decrease (or increase) in group bias. Through simulations as well as real examples on benchmark fairness datasets, we demonstrate that our Fair Feature Importance Score offers valid interpretations for both tree-based ensembles and tree-based surrogates of other ML systems.