A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices

07/02/2018
by   Till Speicher, et al.
0

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2018

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

We draw attention to an important, yet largely overlooked aspect of eval...
research
08/17/2022

Algorithmic Fairness and Statistical Discrimination

Algorithmic fairness is a new interdisciplinary field of study focused o...
research
06/04/2018

iFair: Learning Individually Fair Data Representations for Algorithmic Decision Making

People are rated and ranked, towards algorithmic decision making in an i...
research
12/21/2017

A continuous framework for fairness

Increasingly, discrimination by algorithms is perceived as a societal an...
research
09/03/2019

Quantifying Infra-Marginality and Its Trade-off with Group Fairness

In critical decision-making scenarios, optimizing accuracy can lead to a...
research
06/07/2018

Removing Algorithmic Discrimination (With Minimal Individual Error)

We address the problem of correcting group discriminations within a scor...
research
02/23/2023

Auditing for Spatial Fairness

This paper studies algorithmic fairness when the protected attribute is ...

Please sign up or login with your details

Forgot password? Click here to reset