Group Fairness Is Not Derivable From Justice: a Mathematical Proof

by   Nicolò Cangiotti, et al.

We argue that an imperfect criminal law procedure cannot be group-fair, if 'group fairness' involves ensuring the same chances of acquittal or convictions to all innocent defendants independently of their morally arbitrary features. We show mathematically that only a perfect procedure (involving no mistake), a non-deterministic one, or a degenerate one (everyone or no one is convicted) can guarantee group fairness, in the general case. Following a recent proposal, we adopt a definition of group fairness, requiring that individuals who are equal in merit ought to have the same statistical chances of obtaining advantages and disadvantages, in a way that is statistically independent of any of their feature that does not count as merit. We explain by mathematical argument that the only imperfect procedures offering an a-priori guarantee of fairness in relation to all non-merit trait are lotteries or degenerate ones (i.e., everyone or no one is convicted). To provide a more intuitive point of view, we exploit an adjustment of the well-known ROC space, in order to represent all possible procedures in our model by a schematic diagram. The argument seems to be equally valid for all human procedures, provided they are imperfect. This clearly includes algorithmic decision-making, including decisions based on statistical predictions, since in practice all statistical models are error prone.


page 1

page 2

page 3

page 4


People are not coins. Morally distinct types of predictions necessitate different fairness constraints

A recent paper (Hedden 2021) has argued that most of the group fairness ...

Group Fairness in Prediction-Based Decision Making: From Moral Assessment to Implementation

Ensuring fairness of prediction-based decision making is based on statis...

Bayes-Optimal Classifiers under Group Fairness

Machine learning algorithms are becoming integrated into more and more h...

Taking Advantage of Multitask Learning for Fair Classification

A central goal of algorithmic fairness is to reduce bias in automated de...

Counterpart Fairness – Addressing Systematic between-group Differences in Fairness Evaluation

When using machine learning (ML) to aid decision-making, it is critical ...

De-biasing "bias" measurement

When a model's performance differs across socially or culturally relevan...

Please sign up or login with your details

Forgot password? Click here to reset