Unaware Fairness: Hierarchical Random Forest for Protected Classes
This work addresses fairness concerns in AI systems for applications like law enforcement, but it appears incremental as it builds on existing random forest methods without introducing a fundamentally new paradigm.
The paper tackles the problem of procedural fairness in decision-making regarding protected classes by proposing a hierarchical random forest model that avoids explicit use of such classes, using simulation experiments and an analysis of Boston police interview records to demonstrate its performance and usefulness.
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.