Fair Algorithms for Learning in Allocation Problems
Abstract
Settings such as lending and policing can be modeled by a centralized agent allocating a scarce resource (e.g. loans or police officers) amongst several groups, in order to maximize some objective (e.g. loans given that are repaid, or criminals that are apprehended). Often in such problems fairness is also a concern. One natural notion of fairness, based on general principles of equality of opportunity, asks that conditional on an individual being a candidate for the resource in question, the probability of actually receiving it is approximately independent of the individual's group. For example, in lending this would mean that equally creditworthy individuals in different racial groups have roughly equal chances of receiving a loan. In policing it would mean that two individuals committing the same crime in different districts would have roughly equal chances of being arrested.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Particular choices of models and learning algorithms may be more prone to amplify biases than others.
“particular choices of models and learning algorithms may be more prone to amplify such biases than others”
From Equity and Artificial Intelligence in Education: Will "AIEd" Amplify or Alleviate Inequities in Education? (2021) · cites this paper as Elzayn et al., 2019
Interactions between human and machine biases may have compounding effects, for better or worse, in the presence of human-AI feedback loops in learning or decision-making.
“Such interactions between human and machine biases may have compounding effects - for better or worse - in the presence of human-AI feedback loops in learning or decision-making”
From Equity and Artificial Intelligence in Education: Will "AIEd" Amplify or Alleviate Inequities in Education? (2021) · cites this paper as Elzayn et al., 2019
Cites
Fairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988 · see citing works
Self-citationFairness in Learning: Classic and Contextual Bandits
Joseph, M., Kearns, M., Morgenstern, J., & Roth, A. (2016) · arXiv · doi:10.48550/arxiv.1605.07139 · Cited by 199 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922 · see citing works
A Review on Fairness in Machine Learning
Pessach, D., & Shmueli, E. (2023) · ACM Computing Surveys · doi:10.1145/3494672 · Cited by 598 · see citing works
Fairness in machine learning: A survey
Caton, S., & Haas, C. (2024) · ACM Computing Surveys · doi:10.1145/3616865 · Cited by 646 · see citing works
Fairness in Machine Learning: A Survey
Caton, S., & Haas, C. (2020) · arXiv · doi:10.48550/arxiv.2010.04053 · Cited by 646 · see citing works
Holstein, K., & Doroudi, S. (2021) · arXiv · doi:10.48550/arxiv.2104.12920 · Cited by 29 · see citing works
“Although the source of such disparities may be understood under our second lens to lie in the choices of data used to train these models, particular choices of models and learning algorithms may be more prone to amplify such biases than others (Elzayn et al., 2019).”
BackgroundA Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
Pagan, N., Baumann, J., Elokda, E., De Pasquale, G., Bolognani, S., & Hannák, A. (2023) · arXiv · doi:10.48550/arxiv.2305.06055 · Cited by 4 · see citing works
- Authors
- Elzayn, H., Jabbari, S., Jung, C., Kearns, M., Neel, S., Roth, A., & Schutzman, Z.
- Affiliations
- University of Pennsylvania (US)
- Venue
- Proceedings of the Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2019-01-29
- Pages
- 170-179
- OpenAlex
- W2889252776
- Cited by
- 70
- References
- 2
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 5 · 2023: 11 · 2022: 14 · 2021: 15 · 2020: 12 · 2019: 4 · 2018: 1
- FWCI
- 11.76
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Game Theory and Voting Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › Optimization and Search Problems
- Keywords
- algorithmic fairness, allocation problems, scarce resource allocation, equal opportunities, conditional independence, lending, policing, racial disparities, credit scoring, arrest rates
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
