The measure and mismeasure of fairness
The field of fair machine learning aims to ensure that decisions guided by algorithms are
equitable. Over the last decade, several formal, mathematical definitions of fairness have …
equitable. Over the last decade, several formal, mathematical definitions of fairness have …
Causal conceptions of fairness and their consequences
Recent work highlights the role of causality in designing equitable decision-making
algorithms. It is not immediately clear, however, how existing causal conceptions of fairness …
algorithms. It is not immediately clear, however, how existing causal conceptions of fairness …
Designing equitable algorithms
Predictive algorithms are now commonly used to distribute society's resources and
sanctions. But these algorithms can entrench and exacerbate inequities. To guard against …
sanctions. But these algorithms can entrench and exacerbate inequities. To guard against …
Counterfactual risk assessments, evaluation, and fairness
Algorithmic risk assessments are increasingly used to help humans make decisions in high-
stakes settings, such as medicine, criminal justice and education. In each of these cases, the …
stakes settings, such as medicine, criminal justice and education. In each of these cases, the …
Conditional learning of fair representations
We propose a novel algorithm for learning fair representations that can simultaneously
mitigate two notions of disparity among different demographic subgroups in the classification …
mitigate two notions of disparity among different demographic subgroups in the classification …
Fairness in risk assessment instruments: Post-processing to achieve counterfactual equalized odds
In domains such as criminal justice, medicine, and social welfare, decision makers
increasingly have access to algorithmic Risk Assessment Instruments (RAIs). RAIs estimate …
increasingly have access to algorithmic Risk Assessment Instruments (RAIs). RAIs estimate …
[HTML][HTML] Machine learning interpretability for a stress scenario generation in credit scoring based on counterfactuals
AC Bueff, M Cytryński, R Calabrese, M Jones… - Expert Systems with …, 2022 - Elsevier
To boost the application of machine learning (ML) techniques for credit scoring models, the
blackbox problem should be addressed. The primary aim of this paper is to propose a …
blackbox problem should be addressed. The primary aim of this paper is to propose a …
Breaking feedback loops in recommender systems with causal inference
Recommender systems play a key role in shaping modern web ecosystems. These systems
alternate between (1) making recommendations (2) collecting user responses to these …
alternate between (1) making recommendations (2) collecting user responses to these …
Learning to be fair: A consequentialist approach to equitable decision-making
In the dominant paradigm for designing equitable machine learning systems, one works to
ensure that model predictions satisfy various fairness criteria, such as parity in error rates …
ensure that model predictions satisfy various fairness criteria, such as parity in error rates …
Fade: Fair double ensemble learning for observable and counterfactual outcomes
A Mishler, EH Kennedy - Proceedings of the 2022 ACM Conference on …, 2022 - dl.acm.org
Methods for building fair predictors often involve tradeoffs between fairness and accuracy
and between different fairness criteria. Recent work seeks to characterize these tradeoffs in …
and between different fairness criteria. Recent work seeks to characterize these tradeoffs in …