On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems
This addresses fairness and explainability issues in high-stakes AI systems, offering a method to reveal root causes of unfairness, though it appears incremental as it builds on existing concepts like aptitude.
The paper tackles the problem of explaining proxy discrimination and unfairness in individual AI decisions by proposing a novel framework using formal abductive explanations to identify unjustified proxy features and hidden structural biases, demonstrated with examples from the German credit dataset.
Artificial intelligence (AI) systems in high-stakes domains raise concerns about proxy discrimination, unfairness, and explainability. Existing audits often fail to reveal why unfairness arises, particularly when rooted in structural bias. We propose a novel framework using formal abductive explanations to explain proxy discrimination in individual AI decisions. Leveraging background knowledge, our method identifies which features act as unjustified proxies for protected attributes, revealing hidden structural biases. Central to our approach is the concept of aptitude, a task-relevant property independent of group membership, with a mapping function aligning individuals of equivalent aptitude across groups to assess fairness substantively. As a proof of concept, we showcase the framework with examples taken from the German credit dataset, demonstrating its applicability in real-world cases.