Unaware Fairness: Hierarchical Random Forest for Protected Classes

TL;DR

This paper introduces a hierarchical random forest model that predicts protected classes indirectly through proxies, aiming to enhance fairness in decision-making processes without explicitly using sensitive attributes.

Contribution

The paper proposes a novel hierarchical random forest approach that infers protected classes via proxies, reducing bias and improving fairness in predictive models.

Findings

The hierarchical random forest performs well in simulations.

The model effectively predicts protected classes using proxies.

Application to Boston police data demonstrates practical usefulness.

Abstract

Procedural fairness has been a public concern, which leads to controversy when making decisions with respect to protected classes, such as race, social status, and disability. Some protected classes can be inferred according to some safe proxies like surname and geolocation for the race. Hence, implicitly utilizing the predicted protected classes based on the related proxies when making decisions is an efficient approach to circumvent this issue and seek just decisions. In this article, we propose a hierarchical random forest model for prediction without explicitly involving protected classes. Simulation experiments are conducted to show the performance of the hierarchical random forest model. An example is analyzed from Boston police interview records to illustrate the usefulness of the proposed model.