How Differential Robustness Creates Disparate Impact: A European Case Study

Charles Wan, Leid Zejnilović, Susana Lavado

Research output: Chapter/Conference proceedingConference proceedingAcademicpeer-review

Abstract

We formalize a notion of differential robustness. An algorithm is differentially robust to an event if the event has disparate impact on the performance of an algorithm for different groups in the population. We illustrate it with a case study of the real world deployment of a predictive algorithm in a European public employment service.
Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
Volume3442
Publication statusPublished - 2023
Event2nd European Workshop on Algorithmic Fairness, EWAF 2023 - Winterthur, Switzerland
Duration: 7 Jun 20239 Jun 2023

Conference

Conference2nd European Workshop on Algorithmic Fairness, EWAF 2023
Country/TerritorySwitzerland
CityWinterthur
Period7/06/239/06/23

Bibliographical note

Publisher Copyright:
© 2023 Copyright for this paper by its authors.

Fingerprint

Dive into the research topics of 'How Differential Robustness Creates Disparate Impact: A European Case Study'. Together they form a unique fingerprint.

Cite this