Explainable AI through a Democratic Lens: DhondtXAI for Proportional Feature Importance Using the D'Hondt Method

TL;DR

This paper introduces DhondtXAI, a novel explainability method for AI that applies the D'Hondt proportional representation principle to interpret feature importance, enhancing transparency in healthcare prediction models.

Contribution

It presents a new XAI approach integrating electoral principles, specifically the D'Hondt method, for more interpretable feature attribution in machine learning models.

Findings

DhondtXAI aligns well with SHAP in feature importance attribution.

Proportional representation concepts improve interpretability.

Method enhances understanding in high-stakes healthcare applications.

Abstract

In democratic societies, electoral systems play a crucial role in translating public preferences into political representation. Among these, the D'Hondt method is widely used to ensure proportional representation, balancing fair representation with governmental stability. Recently, there has been a growing interest in applying similar principles of proportional representation to enhance interpretability in machine learning, specifically in Explainable AI (XAI). This study investigates the integration of D'Hondt-based voting principles in the DhondtXAI method, which leverages resource allocation concepts to interpret feature importance within AI models. Through a comparison of SHAP (Shapley Additive Explanations) and DhondtXAI, we evaluate their effectiveness in feature attribution within CatBoost and XGBoost models for breast cancer and diabetes prediction, respectively. The DhondtXAI approach allows for alliance formation and thresholding to enhance interpretability, representing feature importance as seats in a parliamentary view. Statistical correlation analyses between SHAP values and DhondtXAI allocations support the consistency of interpretations, demonstrating DhondtXAI's potential as a complementary tool for understanding feature importance in AI models. The results highlight that integrating electoral principles, such as proportional representation and alliances, into AI explainability can improve user understanding, especially in high-stakes fields like healthcare.