A Feminist Account of Intersectional Algorithmic Fairness

Abstract: Intersectionality has profoundly influenced research and political action by revealing how interconnected systems of privilege and oppression influence lived experiences, yet its integration into algorithmic fairness research remains limited. Existing approaches often rely on single-axis or formal subgroup frameworks that risk oversimplifying social realities and neglecting structural inequalities. We propose Substantive Intersectional Algorithmic Fairness, extending Green's (2022) notion of substantive algorithmic fairness with insights from intersectional feminist theory. Building on this foundation, we introduce ten desiderata within the ROOF methodology to guide the design, assessment, and deployment of algorithmic systems in ways that address systemic inequities while mitigating harms to intersectionally marginalized communities. Rather than prescribing fixed operationalizations, these desiderata encourage reflection on assumptions of neutrality, the use of protected attributes, the inclusion of multiply marginalized groups, and enhancing algorithmic systems' potential. Our approach emphasizes that fairness cannot be separated from social context, and that in some cases, principled non-deployment may be necessary. By bridging computational and social science perspectives, we provide actionable guidance for more equitable, inclusive, and context-sensitive intersectional algorithmic practices.