A Tutorial On Intersectionality in Fair Rankings
Chiara Criscuolo, Davide Martinenghi, Giuseppe Piccirillo
TL;DR
Biased rankings are pervasive across search, recommendation, and hiring systems, and single-attribute fairness is insufficient to eliminate discrimination. The paper surveys three methodological families—Constraint-Based, Inference Model-Based, and Metrics-Based—through practical examples and a synoptic table, emphasizing intersectionality as the interplay of multiple protected attributes. It demonstrates that incorporating intersectionality can achieve fair rankings with minimal utility loss and offers concrete techniques such as diversity constraints, causal counterfactuals, and information-theoretic approaches. The work highlights the importance of moving beyond attribute-wise fairness to intersectional fairness for more equitable data-driven decision-making and provides a roadmap for future research and deployment in real systems.
Abstract
We address the critical issue of biased algorithms and unfair rankings, which have permeated various sectors, including search engines, recommendation systems, and workforce management. These biases can lead to discriminatory outcomes in a data-driven world, especially against marginalized and underrepresented groups. Efforts towards responsible data science and responsible artificial intelligence aim to mitigate these biases and promote fairness, diversity, and transparency. However, most fairness-aware ranking methods singularly focus on protected attributes such as race, gender, or socio-economic status, neglecting the intersectionality of these attributes, i.e., the interplay between multiple social identities. Understanding intersectionality is crucial to ensure that existing inequalities are not preserved by fair rankings. We offer a description of the main ways to incorporate intersectionality in fair ranking systems through practical examples and provide a comparative overview of existing literature and a synoptic table summarizing the various methodologies. Our analysis highlights the need for intersectionality to attain fairness, while also emphasizing that fairness, alone, does not necessarily imply intersectionality.