Measuring Fairness in an Unfair World

Jonathan Herington
University of Rochester
Computer scientists have made great strides in characterizing different measures of algorithmic fairness, and showing that certain measures of fairness cannot be jointly satisfied. In this paper, I argue that the three most popular families of measures - unconditional independence, target-conditional independence and classification-conditional independence - make assumptions that are unsustainable in the context of an unjust world. I begin by introducing the measures and the implicit idealizations they make about the underlying causal structure of the contexts in which they are deployed. I then discuss how these idealizations fall apart in the context of historical injustice, ongoing unmodeled oppression, and the permissibility of using sensitive attributes to rectify injustice. In the final section, I suggest an alternative framework for measuring fairness in the context of existing injustice: distributive fairness.
Keywords fairness  algorithmic decision-making  causal inference  distributive justice  discrimination
Categories (categorize this paper)
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

Upload a copy of this paper     Check publisher's policy     Papers currently archived: 64,261
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

No references found.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles

Democratizing Algorithmic Fairness.Pak-Hang Wong - 2020 - Philosophy and Technology 33 (2):225-244.
Justice as Fairness: Luck Egalitarian, Not Rawlsian.Michael Otsuka - 2010 - The Journal of Ethics 14 (3-4):217-230.
What's Fair About Individual Fairness?Will Fleisher - 2021 - Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society.
Measuring the Biases That Matter: The Ethical and Causal Foundations for Measures of Fairness in Algorithms.Jonathan Herington & Bruce Glymour - 2019 - Proceedings of the Conference on Fairness, Accountability, and Transparency 2019:269-278.
A Moral Framework for Understanding of Fair ML Through Economic Models of Equality of Opportunity.Hoda Heidari - 2019 - Proceedings of the Conference on Fairness, Accountability, and Transparency 1.
Proceed with Caution.Annette Zimmermann & Chad Lee-Stronach - 2021 - Canadian Journal of Philosophy.
Fairness in Allocating the Global Emissions Budget.David R. Morrow - 2017 - Environmental Values 26 (6):669-691.
On Statistical Criteria of Algorithmic Fairness.Brian Hedden - 2021 - Philosophy and Public Affairs 49 (2):209-231.
Fairness. Theory and Practice of Distributive Justice.Ludvig Beckman - 2004 - Review of Metaphysics 58 (1):188-190.


Added to PP index

Total views
1 ( #1,509,497 of 2,455,883 )

Recent downloads (6 months)
1 ( #449,201 of 2,455,883 )

How can I increase my downloads?


Sorry, there are not enough data points to plot this chart.

My notes