mlsanityData to 7 Oct 2026

Fairness in Criminal Justice Risk Assessments: The State of the Art

arXiv 1703.09207 ↗First posted 27 Mar 2017stat.MLcited by 315

Not on the map. Why?

Abstract (arXiv)

Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this paper, we seek to clarify the tradeoffs between different kinds of fairness and between fairness and accuracy. Methods: We draw on the existing literatures in criminology, computer science and statistics to provide an integrated examination of fairness and accuracy in criminal justice risk assessments. We also provide an empirical illustration using data from arraignments. Results: We show that there are at least six kinds of fairness, some of which are incompatible with one another and with accuracy. Conclusions: Except in trivial cases, it is impossible to maximize accuracy and fairness at the same time, and impossible simultaneously to satisfy all kinds of fairness. In practice, a major complication is different base rates across different legally protected groups. There is a need to consider challenging tradeoffs.

Key facts. Cited by 315 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 68; 2022: 64; 2023: 59; 2024: 59; 2025: 43; 2026: 22.

315 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  3. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  4. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  5. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  6. 2021Fair Mixup: Fairness via Interpolationcited by 109
  7. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  8. 2021Trustworthy AI: A Computational Perspectivecited by 93
  9. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
  10. 2021Heterogeneous Risk Minimizationcited by 90
  11. 2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
  12. 2022A Systematic Study of Bias Amplificationcited by 65
38 more
  1. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  2. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  3. 2021Directional Bias Amplificationcited by 54
  4. 2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifierscited by 53
  5. 2022Fair and Optimal Classification via Post-Processingcited by 50
  6. 2022Causal Conceptions of Fairness and their Consequencescited by 38
  7. 2021Selective Regression Under Fairness Criteriacited by 34
  8. 2022A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifierscited by 30
  9. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  10. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  11. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  12. 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
  13. 2021Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Makingcited by 23
  14. 2021Testing Group Fairness via Optimal Transport Projectionscited by 23
  15. 2023Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testingcited by 23
  16. 2021Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systemscited by 20
  17. 2022FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neuronscited by 20
  18. 2023Re-weighting Based Group Fairness Regularization via Classwise Robust Optimizationcited by 20
  19. 2023Rethinking the Evaluation Protocol of Domain Generalizationcited by 20
  20. 2024A Survey on Evaluation of Out-of-Distribution Generalizationcited by 20
  21. 2021Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloudcited by 19
  22. 2022Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiencycited by 19
  23. 2023Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventionscited by 19
  24. 2023Fairness of ChatGPTcited by 19
  25. 2024Auditing the Use of Language Models to Guide Hiring Decisionscited by 19
  26. 2021OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learningcited by 18
  27. 2021Loss-Aversively Fair Classificationcited by 18
  28. 2021A Framework for Fairness: A Systematic Review of Existing Fair AI Solutionscited by 18
  29. 2022Evaluating Proposed Fairness Models for Face Recognition Algorithmscited by 18
  30. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  31. 2022Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problemscited by 18
  32. 2023Improving Recommendation Fairness via Data Augmentationcited by 18
  33. 2024Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classificationcited by 18
  34. 2021Understanding and Mitigating Accuracy Disparity in Regressioncited by 17
  35. 2021Gender and Racial Fairness in Depression Research using Social Mediacited by 17
  36. 2021FairCal: Fairness Calibration for Face Verificationcited by 17
  37. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  38. 2022Towards Understanding Fairness and its Composition in Ensemble Machine Learningcited by 17

50 most cited of 315 All 315 (JSON)