# Unfair Utilities and First Steps Towards Improving Them

arXiv: https://arxiv.org/abs/2306.00636 · HTML: https://mlsanity.com/paper/2306.00636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [A Convex Framework for Fair Regression](https://mlsanity.com/paper/1706.02409/) (2017)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [Foundations of Structural Causal Models with Cycles and Latent Variables](https://mlsanity.com/paper/1611.06221/) (2016)
- [PC-Fairness: A Unified Framework for Measuring Causality-based Fairness](https://mlsanity.com/paper/1910.12586/) (2019)
- [Counterfactual Risk Assessments, Evaluation, and Fairness](https://mlsanity.com/paper/1909.00066/) (2019)
- [The Use and Misuse of Counterfactuals in Ethical Machine Learning](https://mlsanity.com/paper/2102.05085/) (2021)
- [Agent Incentives: A Causal Perspective](https://mlsanity.com/paper/2102.01685/) (2021)
- [Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making](https://mlsanity.com/paper/1806.04959/) (2018)
- [What's Sex Got To Do With Fair Machine Learning?](https://mlsanity.com/paper/2006.01770/) (2020)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [The Unfairness of Fair Machine Learning: Levelling down and strict egalitarianism by default](https://mlsanity.com/paper/2302.02404/) (2023)
- [Fairness in Ranking under Uncertainty](https://mlsanity.com/paper/2107.06720/) (2021)
- [Invariant Policy Learning: A Causal Perspective](https://mlsanity.com/paper/2106.00808/) (2021)
- [Selection, Ignorability and Challenges With Causal Fairness](https://mlsanity.com/paper/2202.13774/) (2022)
- [Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness](https://mlsanity.com/paper/2202.10816/) (2022)
- [A Complete Criterion for Value of Information in Soluble Influence Diagrams](https://mlsanity.com/paper/2202.11629/) (2022)
- [Evaluating Influence Diagrams using LIMIDs](https://mlsanity.com/paper/1301.3881/) (2013)

## Abstract (arXiv)

Many fairness criteria constrain the policy or choice of predictors, which can have unwanted consequences, in particular, when optimizing the policy under such constraints. Here, we in- stead suggest that fairness can be directly analyzed as a property of the utility function. Instead of imposing fairness constraints on the policy, we suggest to simply maximize a utility function satisfying certain fairness properties. Concretely, we define value of information fairness, which prescribes that there must not be an incentive to infer the protected attribute. This principle sug- gests modifying utility functions such that they satisfy value of information fairness. We describe how such modifications can be achieved and discuss consequences for the corresponding optimal policies. We apply our framework to thought experiments and the COMPAS data, demonstrating that focusing on utility functions sometimes provides answers that better align with intuitive judg- ments about what is fair. Moreover, we are not aware of any intuitively fair policy that violates value of information fairness; and when we find that value of information fairness recommends an intuitively unfair policy, no realizable policy is intuitively fair.