How to be fair? A study of label and selection bias
Authors:
- 20 September 2023
- journal article
- research article
- Published by Springer Nature in Machine Learning
- Vol. 112 (12) , 5081-5104
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- AXA Research Fund
This publication has 14 references indexed in Scilit:
- Why fairness cannot be automated: Bridging the gap between EU non-discrimination law and AIComputer Law & Security Review, 2021
- The (Im)possibility of fairnessCommunications of the ACM, 2021
- Dissecting racial bias in an algorithm used to manage the health of populationsScience, 2019
- FAIRVIS: Visual Analytics for Discovering Intersectional Bias in Machine Learning2019
- AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic biasIBM Journal of Research and Development, 2019
- Mitigating Unwanted Biases with Adversarial Learning2018
- Algorithmic Decision Making and the Cost of Fairness2017
- Certifying and Removing Disparate Impact2015
- Data preprocessing techniques for classification without discriminationKnowledge and Information Systems, 2011
- Three naive Bayes approaches for discrimination-free classificationData Mining and Knowledge Discovery, 2010