Fairness through the lens of proportional equality

Biswas, A and Mukherjee, S (2019) Fairness through the lens of proportional equality. In: 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019, 13 - 17 May 2019, Montreal, pp. 1832-1834.

PDF AAMAS_2019.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Today, automated algorithms, such as machine learning classifiers, are playing an increasingly pivotal role in important societal decisions such as hiring, loan allocation, and criminal risk assessment. This motivates the need to probe the outcomes of a prediction model for discriminatory traits towards specific groups of individuals. In this context, one of the crucial challenges is to formally define a satisfactory notion of fairness. Our contribution in this paper is to formalize Proportional Equality (PE) as a fairness notion. We additionally show that it is a more appropriate criterion than the existing popular notion called Disparate Impact (DI), which is used for evaluating the fairness of a classifier's outcomes.

Item Type:	Conference Paper
Publication:	Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Publisher:	International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Additional Information:	The copyright for this article belongs to International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Keywords:	Classification (of information); Machine learning; Multi agent systems; Risk assessment, Discrimination; Fairness concepts; Gender bias; Prior probability; Racial bias, Autonomous agents
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	05 Dec 2022 06:16
Last Modified:	05 Dec 2022 06:16
URI:	https://eprints.iisc.ac.in/id/eprint/78213

Actions (login required)

View Item