Uncertainty-Aware Fairness-Adaptive Classification Trees

TL;DR

This paper introduces a fairness-aware classification tree algorithm that incorporates uncertainty in fairness metrics to reduce discrimination while maintaining accuracy.

Contribution

It presents a novel splitting criterion that accounts for fairness and uncertainty, improving fairness in decision trees.

Findings

Reduces discriminatory predictions compared to traditional trees.

Balances fairness and accuracy effectively.

Utilizes confidence intervals to handle fairness uncertainty.

Abstract

In an era where artificial intelligence and machine learning algorithms increasingly impact human life, it is crucial to develop models that account for potential discrimination in their predictions. This paper tackles this problem by introducing a new classification tree algorithm using a novel splitting criterion that incorporates fairness adjustments into the tree-building process. The proposed method integrates a fairness-aware impurity measure that balances predictive accuracy with fairness across protected groups. By ensuring that each splitting node considers both the gain in classification error and the fairness, our algorithm encourages splits that mitigate discrimination. Importantly, in penalizing unfair splits, we account for the uncertainty in the fairness metric by utilizing its confidence interval instead of relying on its point estimate. Experimental results on benchmark and synthetic datasets illustrate that our method effectively reduces discriminatory predictions compared to traditional classification trees, without significant loss in overall accuracy.