# Fair Classification and Social Welfare

arXiv: https://arxiv.org/abs/1905.00147 · HTML: https://mlsanity.com/paper/1905.00147/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2019.

## Built on by (most cited first, 30 of 40)

- [Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias](https://mlsanity.com/paper/2403.07857/) (2024)
- [Improving the Fairness of Chest X-ray Classifiers](https://mlsanity.com/paper/2203.12609/) (2022)
- [Information Discrepancy in Strategic Learning](https://mlsanity.com/paper/2103.01028/) (2021)
- [The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations](https://mlsanity.com/paper/2205.03295/) (2022)
- [Two-sided fairness in rankings via Lorenz dominance](https://mlsanity.com/paper/2110.15781/) (2021)
- [A Sociotechnical View of Algorithmic Fairness](https://mlsanity.com/paper/2110.09253/) (2021)
- [Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systems](https://mlsanity.com/paper/2103.06172/) (2021)
- [An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning](https://mlsanity.com/paper/2104.14504/) (2021)
- [Removing biased data to improve fairness and accuracy](https://mlsanity.com/paper/2102.03054/) (2021)
- [Optimizing generalized Gini indices for fairness in rankings](https://mlsanity.com/paper/2204.06521/) (2022)
- [A comparison of approaches to improve worst-case predictive model performance over patient subpopulations](https://mlsanity.com/paper/2108.12250/) (2021)
- [Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation](https://mlsanity.com/paper/2210.02516/) (2022)
- [Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing](https://mlsanity.com/paper/2104.01634/) (2021)
- [Addressing Strategic Manipulation Disparities in Fair Classification](https://mlsanity.com/paper/2205.10842/) (2022)
- [Are There Exceptions to Goodhart's Law? On the Moral Justification of Fairness-Aware Machine Learning](https://mlsanity.com/paper/2202.08536/) (2022)
- [When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction](https://mlsanity.com/paper/2206.02058/) (2022)
- [COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation](https://mlsanity.com/paper/2210.15500/) (2022)
- [Disaggregated Interventions to Reduce Inequality](https://mlsanity.com/paper/2107.00593/) (2021)
- [Counterfactuals for the Future](https://mlsanity.com/paper/2212.03974/) (2022)
- [Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities](https://mlsanity.com/paper/2301.05753/) (2023)
- [Regulatory Instruments for Fair Personalized Pricing](https://mlsanity.com/paper/2202.04245/) (2022)
- [(Im)possibility of Collective Intelligence](https://mlsanity.com/paper/2206.02786/) (2022)
- [A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier](https://mlsanity.com/paper/2310.12785/) (2023)
- [Fairness through Social Welfare Optimization](https://mlsanity.com/paper/2102.00311/) (2021)
- [A Justice-Based Framework for the Analysis of Algorithmic Fairness-Utility Trade-Offs](https://mlsanity.com/paper/2206.02891/) (2022)
- [Distributive Justice as the Foundational Premise of Fair ML: Unification, Extension, and Interpretation of Group Fairness Metrics](https://mlsanity.com/paper/2206.02897/) (2022)
- [The Statistical Fairness-Accuracy Frontier](https://mlsanity.com/paper/2508.17622/) (2025)
- [Everything is Relative: Understanding Fairness with Optimal Transport](https://mlsanity.com/paper/2102.10349/) (2021)
- [Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap](https://mlsanity.com/paper/2502.11981/) (2025)
- [Fair Clustering: Critique, Caveats, and Future Directions](https://mlsanity.com/paper/2406.15960/) (2024)

## Abstract (arXiv)

Now that machine learning algorithms lie at the center of many resource allocation pipelines, computer scientists have been unwittingly cast as partial social planners. Given this state of affairs, important questions follow. What is the relationship between fairness as defined by computer scientists and notions of social welfare? In this paper, we present a welfare-based analysis of classification and fairness regimes. We translate a loss minimization program into a social welfare maximization problem with a set of implied welfare weights on individuals and groups--weights that can be analyzed from a distribution justice lens. In the converse direction, we ask what the space of possible labelings is for a given dataset and hypothesis class. We provide an algorithm that answers this question with respect to linear hyperplanes in ℝd that runs in O(ndd). Our main findings on the relationship between fairness criteria and welfare center on sensitivity analyses of fairness-constrained empirical risk minimization programs. We characterize the ranges of Delta ε perturbations to a fairness parameter ε that yield better, worse, and neutral outcomes in utility for individuals and by extension, groups. We show that applying more strict fairness criteria that are codified as parity constraints, can worsen welfare outcomes for both groups. More generally, always preferring "more fair" classifiers does not abide by the Pareto Principle---a fundamental axiom of social choice theory and welfare economics. Recent work in machine learning has rallied around these notions of fairness as critical to ensuring that algorithmic systems do not have disparate negative impact on disadvantaged social groups. By showing that these constraints often fail to translate into improved outcomes for these groups, we cast doubt on their effectiveness as a means to ensure justice.