mlsanityData to 7 Oct 2026

Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

arXiv 1610.07524 ↗First posted 24 Oct 2016stat.AP cs.CY stat.MLcited by 671

Not on the map. Why?

Abstract (arXiv)

Recidivism prediction instruments provide decision makers with an assessment of the likelihood that a criminal defendant will reoffend at a future point in time. While such instruments are gaining increasing popularity across the country, their use is attracting tremendous controversy. Much of the controversy concerns potential discriminatory bias in the risk assessments that are produced. This paper discusses a fairness criterion originating in the field of educational and psychological testing that has recently been applied to assess the fairness of recidivism prediction instruments. We demonstrate how adherence to the criterion may lead to considerable disparate impact when recidivism prevalence differs across groups.

Key facts. Cited by 671 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 125; 2022: 150; 2023: 112; 2024: 102; 2025: 98; 2026: 84.

671 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  4. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  5. 2021Trustworthy AI: From Principles to Practicescited by 206
  6. 2021Simple data balancing achieves competitive worst-group-accuracycited by 177
  7. 2021A survey on datasets for fairness-aware machine learningcited by 157
  8. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  9. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  10. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  11. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  12. 2025LLM Social Simulations Are a Promising Research Methodcited by 97
38 more
  1. 2021Trustworthy AI: A Computational Perspectivecited by 93
  2. 2024Large Language Models are Geographically Biasedcited by 91
  3. 2021A Survey on Bias in Visual Datasetscited by 84
  4. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  5. 2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
  6. 2022A Systematic Study of Bias Amplificationcited by 65
  7. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  8. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
  9. 2024Fairness Feedback Loops: Training on Synthetic Data Amplifies Biascited by 55
  10. 2021Directional Bias Amplificationcited by 54
  11. 2023Towards Last-layer Retraining for Group Robustness with Fewer Annotationscited by 54
  12. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  13. 2021Understanding and Mitigating Annotation Bias in Facial Expression Recognitioncited by 50
  14. 2022Fair and Optimal Classification via Post-Processingcited by 50
  15. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  16. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 48
  17. 2021Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffscited by 48
  18. 2022Evaluation Gaps in Machine Learning Practicecited by 48
  19. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  20. 2021Deep Cox Mixtures for Survival Regressioncited by 43
  21. 2021Fairness of Exposure in Stochastic Banditscited by 42
  22. 2021Multi-group Agnostic PAC Learnabilitycited by 42
  23. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  24. 2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
  25. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  26. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  27. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  28. 2021Assessing Multilingual Fairness in Pre-trained Multimodal Representationscited by 35
  29. 2021Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Researchcited by 34
  30. 2021TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networkscited by 34
  31. 2021Selective Regression Under Fairness Criteriacited by 34
  32. 2021Improved Approximation Algorithms for Individually Fair Clusteringcited by 33
  33. 2022Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkitscited by 33
  34. 2023FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methodscited by 33
  35. 2021RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHRcited by 32
  36. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  37. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
  38. 2022Fairness in Recommender Systems: Research Landscape and Future Directionscited by 30

50 most cited of 671 All 671 (JSON)