Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

Chouldechova, Alexandra

doi:10.48550/arxiv.1703.00056

Cited by 31 publications

(72 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proof: The proof of this result is almost identical to the proof of the previous lemma with the only changes that • = • 2 and that we stop after applying (23) to (21).…”

Section: B Slowly Varying Unknown Noise Covariancementioning

confidence: 67%

Covariance-Robust Dynamic Watermarking

Olfat¹,

Sloan²,

Hespanhol³

et al. 2020

Preprint

View full text Add to dashboard Cite

Attack detection and mitigation strategies for cyberphysical systems (CPS) are an active area of research, and researchers have developed a variety of attack-detection tools such as dynamic watermarking. However, such methods often make assumptions that are difficult to guarantee, such as exact knowledge of the distribution of measurement noise.Here, we develop a new dynamic watermarking method that we call covariance-robust dynamic watermarking, which is able to handle uncertainties in the covariance of measurement noise. Specifically, we consider two cases. In the first this covariance is fixed but unknown, and in the second this covariance is slowly-varying. For our tests, we only require knowledge of a set within which the covariance lies. Furthermore, we connect this problem to that of algorithmic fairness and the nascent field of fair hypothesis testing, and we show that our tests satisfy some notions of fairness. Finally, we exhibit the efficacy of our tests on empirical examples chosen to reflect values observed in a standard simulation model of autonomous vehicles.

show abstract

“…Proof: The proof of this result is almost identical to the proof of the previous lemma with the only changes that • = • 2 and that we stop after applying (23) to (21).…”

Section: B Slowly Varying Unknown Noise Covariancementioning

confidence: 67%

Covariance-Robust Dynamic Watermarking

Olfat¹,

Sloan²,

Hespanhol³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Three of them have been considered both in the literature and in the popular press: equalizing false positive rates, false negative rates, and positive predictive value. These three notions of fairness are of particular interest to us because it has been shown that attaining all three measures simultaneously is impossible (Kleinberg et al [2016], Chouldechova [2017]). Given a policy β g for group g, true positive rate (TPR), false positive rate (FPR), false negative rate (FNR), and positive predictive value (PPV) are defined as…”

Section: Fairness Measuresmentioning

confidence: 99%

“…ProPublica argued that the algorithm's predictions did not maintain parity in false positive and false negative rates between white and black defendants, 1 while Northpointe countered that their algorithm satisfied predictive parity. 2 Subsequent research identified hard trade-offs in the choice of fairness metrics: under some mild conditions, the two requirements above cannot simultaneously be satisfied (Kleinberg et al [2016], Chouldechova [2017]). This inspired a literature proposing (or criticizing) notions of fairness based on ethical/ normative grounds.…”

Section: Introductionmentioning

confidence: 99%

“…3 In general, the different proposed fairness measures are fundamentally at odds with one another. For example, in addition to the impossibility results due to Kleinberg et al [2016], Chouldechova [2017], enforcing parity of false positive or false negative rates for e.g. parole decisions typically requires making parole decisions using different thresholds on the posterior probability that an individual will commit a crime for different groups.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fair Prediction with Endogenous Behavior

Jung¹,

Kannan²,

Lee³

et al. 2020

Preprint

View full text Add to dashboard Cite

There is increasing regulatory interest in whether machine learning algorithms deployed in consequential domains (e.g. in criminal justice) treat different demographic groups "fairly." However, there are several proposed notions of fairness, typically mutually incompatible. Using criminal justice as an example, we study a model in which society chooses an incarceration rule. Agents of different demographic groups differ in their outside options (e.g. opportunity for legal employment) and decide whether to commit crimes. We show that equalizing type I and type II errors across groups is consistent with the goal of minimizing the overall crime rate; other popular notions of fairness are not.

show abstract

“…Numerous mathematical definitions of fairness have been proposed; examples include demographic parity [Dwork et al, 2012], disparate impact [Zafar et al, 2017], equality of odds [Hardt et al, 2016;Feldman et al, 2015], and calibration [Kleinberg et al, 2017]. While each of these notions is appealing on its own, it has been shown that they are incompatible with one another and cannot hold simultaneously [Kleinberg et al, 2017;Chouldechova, 2017]. The literature so far has dealt with these impossibility results by attempting to quantify the tradeoffs between different formulations of fairness, hoping that practitioners will be better positioned to determine the extent to which the violation of each fairness criterion can be socially tolerated (see, e.g., [Corbett-Davies et al, 2017]).…”

Section: Introductionmentioning

confidence: 99%

Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Srivastava¹,

Heidari²,

Krause³

2019

Preprint

View full text Add to dashboard Cite

Fairness for Machine Learning has received considerable attention, recently. Various mathematical formulations of fairness have been proposed, and it has been shown that it is impossible to satisfy all of them simultaneously. The literature so far has dealt with these impossibility results by quantifying the tradeoffs between different formulations of fairness. Our work takes a different perspective on this issue. Rather than requiring all notions of fairness to (partially) hold at the same time, we ask which one of them is the most appropriate given the societal domain in which the decision-making model is to be deployed. We take a descriptive approach and set out to identify the notion of fairness that best captures lay people's perception of fairness. We run adaptive experiments designed to pinpoint the most compatible notion of fairness with each participant's choices through a small number of tests. Perhaps surprisingly, we find that the most simplistic mathematical definition of fairness-namely, demographic parity-most closely matches people's idea of fairness in two distinct application scenarios. This conclusion remains intact even when we explicitly tell the participants about the alternative, more complicated definitions of fairness, and we reduce the cognitive burden of evaluating those notions for them. Our findings have important implications for the Fair ML literature and the discourse on formalizing algorithmic fairness.

show abstract

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

Cited by 31 publications

References 0 publications

Covariance-Robust Dynamic Watermarking

Covariance-Robust Dynamic Watermarking

Fair Prediction with Endogenous Behavior

Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Contact Info

Product

Resources

About