Facets of Disparate Impact: Evaluating Legally Consistent Bias in Machine Learning
This work addresses the need for legally consistent bias evaluation in machine learning, particularly for high-stakes domains like criminal justice, though it appears incremental as it builds on existing legal frameworks.
The paper tackled the problem of evaluating bias in machine learning by introducing the 'Objective Fairness Index', a novel metric that combines legal standards with contextual nuances, and applied it to sensitive applications like COMPAS recidivism prediction to differentiate discriminatory tests from systemic disparities.
Leveraging current legal standards, we define bias through the lens of marginal benefits and objective testing with the novel metric "Objective Fairness Index". This index combines the contextual nuances of objective testing with metric stability, providing a legally consistent and reliable measure. Utilizing the Objective Fairness Index, we provide fresh insights into sensitive machine learning applications, such as COMPAS (recidivism prediction), highlighting the metric's practical and theoretical significance. The Objective Fairness Index allows one to differentiate between discriminatory tests and systemic disparities.