Fairness definitions explained

Verma, Sahil; Rubin, Julia

doi:10.1145/3194770.3194776

Cited by 760 publications

(659 citation statements)

References 9 publications

Supporting

Mentioning

640

Contrasting

Unclassified

Order By: Relevance

“…Previous work has enumerated metrics for evaluating bias [27,58], explored inherent conflicts in satisfying them [12,30], and described case studies and applications to a variety of problems [6,14,30,46]. The main contributions of this work include our framework for equity analysis, methods for balancing equity with other goals such as efficiency and effectiveness, and the application of this framework and methods to a public policy problem.…”

Section: Machine Learning In Criminal Justicementioning

confidence: 99%

“…Much has been written about the competing (and often mutually exclusive) concepts of fairness in machine learning problems [12,27,30,58]. In the context of recidivism prediction, this debate has focused primarily on punitive applications, such as risk scores being used to deny defendants bail or even to assign harsher sentences to individuals with higher risk.…”

Section: Predictive Fairness 51 Measuring Fairnessmentioning

confidence: 99%

See 1 more Smart Citation

Case study

Rodolfa

Salomon

Haynes

et al. 2020

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

The criminal justice system is currently ill-equipped to improve outcomes of individuals who cycle in and out of the system with a series of misdemeanor offenses. Often due to constraints of caseload and poor record linkage, prior interactions with an individual may not be considered when an individual comes back into the system, let alone in a proactive manner through the application of diversion programs. The Los Angeles City Attorney's Office recently created a new Recidivism Reduction and Drug Diversion unit (R2D2) tasked with reducing recidivism in this population. Here we describe a collaboration with this new unit as a case study for the incorporation of predictive equity into machine learning based decision making in a resource-constrained setting. The program seeks to improve outcomes by developing individually-tailored social service interventions (i.e., diversions, conditional plea agreements, stayed sentencing, or other favorable case disposition based on appropriate social service linkage rather than traditional sentencing methods) for individuals likely to experience subsequent interactions with the criminal justice system, a time and resource-intensive undertaking that necessitates an ability to focus resources on individuals most likely to be involved in a future case. Seeking to achieve both efficiency (through predictive accuracy) and equity (improving outcomes in traditionally under-served communities and working to mitigate existing disparities in criminal justice outcomes), we discuss the equity outcomes we seek to achieve, describe the corresponding choice of a metric for measuring predictive fairness in this context, and explore a set of options for balancing equity and efficiency when building and selecting machine learning models in an operational public policy setting. CCS CONCEPTS• Applied computing → Computing in government; Law, social and behavioral sciences; • Social and professional topics →

show abstract

Section: Machine Learning In Criminal Justicementioning

confidence: 99%

Section: Predictive Fairness 51 Measuring Fairnessmentioning

confidence: 99%

Case study

Rodolfa

Salomon

Haynes

et al. 2020

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

show abstract

“…For algorithms that allocate people to favored or less favored groups, many researchers have explored different ways of measuring and ensuring fairness in how the favorable outcomes are assigned (Dwork, Hardt, Pitassi, Reingold, & Zemel, 2012;Verma & Rubin, 2018).…”

Section: Allocative Fairn Essmentioning

confidence: 99%

Workshop on AI fairness for people with disabilities

Trewin¹,

Morris²,

Branham³

et al. 2020

SIGACCESS Access. Comput.

View full text Add to dashboard Cite

We consider how fair treatment in society for people with disabilities might be impacted by the rise in the use of artificial intelligence, and especially machine learning methods. We argue that fairness for people with disabilities is different to fairness for other protected attributes such as age, gender or race. One major difference is the extreme diversity of ways disabilities manifest, and people adapt. Secondly, disability information is highly sensitive and not always shared, precisely because of the potential for discrimination. Given these differences, we explore definitions of fairness and how well they work in the disability space. Finally, we suggest ways of approaching fairness for people with disabilities in AI applications.

show abstract

“…Although more than twenty different notions of fairness have been proposed in the last few years [25,29], still there is no agreement on which measure to apply in each situation. The most popular is that of statistical parity [29] that checks whether the favored and deprived communities have equal probability of being assigned to the positive class. This is the measure we also adopt in this work.…”

Section: Related Workmentioning

confidence: 99%

Fairness-Enhancing Interventions in Stream Classification

Iosifidis

Tran

Ntoutsi

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle fairness as a batch learning problem and aim at learning a fair model which can then be applied to future instances of the problem. In many applications, however, the data comes sequentially and its characteristics might evolve with time.In such a setting, it is counter-intuitive to "fix" a (fair) model over the data stream as changes in the data might incur changes in the underlying model therefore, affecting its fairness. In this work, we propose fairnessenhancing interventions that modify the input data so that the outcome of any stream classifier applied to that data will be fair. Experiments on real and synthetic data show that our approach achieves good predictive performance and low discrimination scores over the course of the stream.

show abstract

Fairness definitions explained

Cited by 760 publications

References 9 publications

Case study

Case study

Workshop on AI fairness for people with disabilities

Fairness-Enhancing Interventions in Stream Classification

Contact Info

Product

Resources

About