# Randomized Classifiers vs Human Decision-Makers: Trustworthy AI May Have to Act Randomly and Society Seems to Accept This

arXiv: https://arxiv.org/abs/2111.07545 · HTML: https://mlsanity.com/paper/2111.07545/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 149 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 12 of 12)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity](https://mlsanity.com/paper/1809.03400/) (2018)
- [The social dilemma of autonomous vehicles](https://mlsanity.com/paper/1510.03346/) (2015)
- [On Automating the Doctrine of Double Effect](https://mlsanity.com/paper/1703.08922/) (2017)
- [The AI Liability Puzzle and A Fund-Based Work-Around](https://mlsanity.com/paper/1911.08005/) (2019)
- [Harnessing Higher-Order (Meta-)Logic to Represent and Reason with Complex Ethical Theories](https://mlsanity.com/paper/1903.09818/) (2019)

## Built on by (most cited first, 1 of 1)

- [Algorithmic Censoring in Dynamic Learning Systems](https://mlsanity.com/paper/2305.09035/) (2023)

## Abstract (arXiv)

As artificial intelligence (AI) systems are increasingly involved in decisions affecting our lives, ensuring that automated decision-making is fair and ethical has become a top priority. Intuitively, we feel that akin to human decisions, judgments of artificial agents should necessarily be grounded in some moral principles. Yet a decision-maker (whether human or artificial) can only make truly ethical (based on any ethical theory) and fair (according to any notion of fairness) decisions if full information on all the relevant factors on which the decision is based are available at the time of decision-making. This raises two problems: (1) In settings, where we rely on AI systems that are using classifiers obtained with supervised learning, some induction/generalization is present and some relevant attributes may not be present even during learning. (2) Modeling such decisions as games reveals that any -- however ethical -- pure strategy is inevitably susceptible to exploitation. Moreover, in many games, a Nash Equilibrium can only be obtained by using mixed strategies, i.e., to achieve mathematically optimal outcomes, decisions must be randomized. In this paper, we argue that in supervised learning settings, there exist random classifiers that perform at least as well as deterministic classifiers, and may hence be the optimal choice in many circumstances. We support our theoretical results with an empirical study indicating a positive societal attitude towards randomized artificial decision-makers, and discuss some policy and implementation issues related to the use of random classifiers that relate to and are relevant for current AI policy and standardization initiatives.