Bias on demand: a modelling framework that generates synthetic data with bias
Nowadays, Machine Learning (ML) systems are widely used in various businesses and are
increasingly being adopted to make decisions that can significantly impact people's lives …
increasingly being adopted to make decisions that can significantly impact people's lives …
Group fairness: Independence revisited
T Räz - Proceedings of the 2021 ACM conference on fairness …, 2021 - dl.acm.org
This paper critically examines arguments against independence, a measure of group
fairness also known as statistical parity and as demographic parity. In recent discussions of …
fairness also known as statistical parity and as demographic parity. In recent discussions of …
Fairness and risk: an ethical argument for a group fairness definition insurers can use
Algorithmic predictions are promising for insurance companies to develop personalized risk
models for determining premiums. In this context, issues of fairness, discrimination, and …
models for determining premiums. In this context, issues of fairness, discrimination, and …
Distributive justice as the foundational premise of fair ML: Unification, extension, and interpretation of group fairness metrics
Group fairness metrics are an established way of assessing the fairness of prediction-based
decision-making systems. However, these metrics are still insufficiently linked to …
decision-making systems. However, these metrics are still insufficiently linked to …
Group fairness in prediction-based decision making: From moral assessment to implementation
Ensuring fairness of prediction-based decision making is based on statistical group fairness
criteria. Which one of these criteria is the morally most appropriate one depends on the …
criteria. Which one of these criteria is the morally most appropriate one depends on the …
The fairness in algorithmic fairness
S Holm - Res Publica, 2023 - Springer
With the increasing use of algorithms in high-stakes areas such as criminal justice and
health has come a significant concern about the fairness of prediction-based decision …
health has come a significant concern about the fairness of prediction-based decision …
Rawlsnet: Altering bayesian networks to encode rawlsian fair equality of opportunity
We present RAWLSNET, a system for altering Bayesian Network (BN) models to satisfy the
Rawlsian principle of fair equality of opportunity (FEO). RAWLSNET's BN models generate …
Rawlsian principle of fair equality of opportunity (FEO). RAWLSNET's BN models generate …
Gradual (in) compatibility of fairness criteria
C Hertweck, T Räz - Proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Impossibility results show that important fairness measures (independence, separation,
sufficiency) cannot be satisfied at the same time under reasonable assumptions. This paper …
sufficiency) cannot be satisfied at the same time under reasonable assumptions. This paper …
On prediction-modelers and decision-makers: why fairness requires more than a fair prediction model
An implicit ambiguity in the field of prediction-based decision-making concerns the relation
between the concepts of prediction and decision. Much of the literature in the field tends to …
between the concepts of prediction and decision. Much of the literature in the field tends to …
Bias and fairness in machine learning and artificial intelligence
D Cirillo, MJ Rementeria - Sex and gender bias in technology and artificial …, 2022 - Elsevier
Sex and gender biases can be entrenched in the life cycle of Artificial Intelligence (AI)
development, from data acquisition to technological design and deployment. AI systems that …
development, from data acquisition to technological design and deployment. AI systems that …