The price of fairness - A framework to explore trade-offs in algorithmic fairness

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

With the increase in automated decision making using predictive analytics, the aspect of fairness of the resulting predictions for specific groups is increasingly considered in research and practice. Currently, the actual trade-off to achieve fairness, or a certain level of fairness, is not well understood, other than that an increase in fairness typically decreases other predictive analytics metrics such as accuracy. To enable a systematic evaluation of potential trade-offs between fairness and other metrics, a framework for exploring Algorithmic Fairness is proposed. Using a combination of multi-objective optimization and Pareto fronts, the framework allows for the exploration of fairness-performance trade-offs and enables the systematic comparison of different algorithmic techniques to increase fairness. A case study compares several fairness metrics and different algorithmic techniques, provides insight into trade-offs found between metrics, and shows how the framework can be leveraged to find a 'best' level of fairness for a given scenario.

Original languageEnglish (US)
Title of host publication40th International Conference on Information Systems, ICIS 2019
PublisherAssociation for Information Systems
ISBN (Electronic)9780996683197
StatePublished - 2020
Event40th International Conference on Information Systems, ICIS 2019 - Munich, Germany
Duration: Dec 15 2019Dec 18 2019

Publication series

Name40th International Conference on Information Systems, ICIS 2019

Conference

Conference40th International Conference on Information Systems, ICIS 2019
Country/TerritoryGermany
CityMunich
Period12/15/1912/18/19

Keywords

  • Algorithmic Fairness
  • Bias Mitigation
  • Multi-objective Optimization

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'The price of fairness - A framework to explore trade-offs in algorithmic fairness'. Together they form a unique fingerprint.

Cite this