How fair can we go in machine learning ? Assessing the boundaries of accuracy and fairness
Authors:
Open Access
- 1 January 2021
- journal article
- research article
- Published by Hindawi Limited in International Journal of Intelligent Systems
- Vol. 36 (4) , 1619-1643
Abstract
Fair machine learning has been focusing on the development of equitable algorithms that address discrimination. Yet, many of these fairness‐aware approaches aim to obtain a unique solution to the problem, which leads to a poor understanding of the statistical limits of bias mitigation interventions. In this study, a novel methodology is presented to explore the tradeoff in terms of a Pareto front between accuracy and fairness. To this end, we propose a multiobjective framework that seeks to optimize both measures. The experimental framework is focused on logistiregression and decision tree classifiers since they are well‐known by the machine learning community. We conclude experimentally that our method can optimize classifiers by being fairer with a small cost on the classification accuracy. We believe that our contribution will help stakeholders of sociotechnical systems to assess how far they can go being fair and accurate, thus serving in the support of enhanced decision making where machine learning is used.Keywords
All Related Versions
Funding Information
- H2020 European Research Council (759903)
- Ministerio de Ciencia e Innovación
- Instituto de Salud Carlos III (PI20/01435)
This publication has 17 references indexed in Scilit:
- Fair classification and social welfare2020
- What does it mean to 'solve' the problem of discrimination in hiring?2020
- Matching code and law: achieving algorithmic fairness with optimal transportData Mining and Knowledge Discovery, 2019
- WE-Rec: A fairness-aware reciprocal recommendation based on Walrasian equilibriumKnowledge-Based Systems, 2019
- A comparative study of fairness-enhancing interventions in machine learning2019
- Model Cards for Model Reporting2019
- Fairness and Abstraction in Sociotechnical Systems2019
- 'It's Reducing a Human Being to a Percentage'2018
- Fairness Beyond Disparate Treatment & Disparate Impact2017
- Discrimination Aware Decision Tree Learning2010