Explainable AI through a Democratic Lens: DhondtXAI for Proportional Feature Importance Using the D'Hondt Method
This work addresses the need for more interpretable AI models in high-stakes domains like healthcare by introducing a novel method based on electoral principles, though it appears incremental as an adaptation of existing concepts to XAI.
This paper tackles the problem of improving interpretability in Explainable AI (XAI) by proposing DhondtXAI, a method that applies the D'Hondt electoral system's proportional representation principles to allocate feature importance in AI models like CatBoost and XGBoost for healthcare predictions. The results show statistical correlation with SHAP values, supporting DhondtXAI as a complementary tool for enhancing user understanding in fields such as healthcare.
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.