Counterfactual Fairness

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.

• Publication year

  2017

• Venue

  Neural Information Processing Systems

• Publication date

  2017-03-20

• Fields of study

  Law, Computer Science, Mathematics, Philosophy, Psychology

• Identifiers
  arXiv 1703.06856
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

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

  2017cited by this paper
• When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness

  2017cited by this paper
• Fair Inference on Outcomes

  2017cited by this paper
• Avoiding Discrimination through Causal Reasoning

  2017influential reference
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

  2016cited by this paper
• Structural Equations With Latent Variables

  2016cited by this paper
• The Case for Process Fairness in Learning: Feature Selection for Fair Decision Making

  2016cited by this paper
• Causal Inference in Statistics: A Primer

  2016influential reference
• Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments

  2016cited by this paper
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

  2016cited by this paper
• Impartial Predictive Modeling: Ensuring Fairness in Arbitrary Models

  2016cited by this paper
• Equality of Opportunity in Supervised Learning

  2016cited by this paper
• Inherent Trade-Offs in the Fair Determination of Risk Scores

  2016cited by this paper
• Rawlsian Fairness for Machine Learning

  2016cited by this paper
• Actual Causality

  2016cited by this paper
• The Variational Fair Autoencoder

  2015cited by this paper
• A survey on measuring indirect discrimination in machine learning

  2015cited by this paper
• Learning Fair Classifiers

  2015cited by this paper
• "Wrong side of the tracks": Big Data and Protected Categories

  2014cited by this paper
• Causal Inference through a Witness Protection Program

  2014cited by this paper
• Commentary: race and sex are causes.

  2014cited by this paper
• Causal discovery with continuous additive noise models

  2013cited by this paper
• Learning Fair Representations

  2013cited by this paper
• Fairness-aware Learning through Regularization Approach

  2011cited by this paper
• Fairness through awareness

  2011cited by this paper
• Data preprocessing techniques for classification without discrimination

  2011cited by this paper
• Posterior Regularization for Structured Latent Variable Models

  2010cited by this paper
• Consumer Credit Risk Models Via Machine-Learning Algorithms

  2010cited by this paper
• Three naive Bayes approaches for discrimination-free classification

  2010cited by this paper
• Evaluating the Predictive Validity of the Compas Risk and Needs Assessment System

  2009cited by this paper
• Classifying without discriminating

  2009cited by this paper
• Causal inference in statistics: An overview

  2009influential reference
• Regression by dependence minimization and its application to causal inference in additive noise models

  2009cited by this paper
• Causal Inference without Counterfactuals

  2000cited by this paper
• LSAC National Longitudinal Bar Passage Study. LSAC Research Report Series.

  1998cited by this paper
• Testing Structural Equation Models

  1993cited by this paper
• Counterfactuals

  1974cited by this paper
• Causality : Models , Reasoning , and Inference

  year unknowninfluential reference

• Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness

  2026influential citation
• Rethinking Item Fairness Using Single World Intervention Graphs

  2026cites this paper
• A speculative realist typology of AI fairness: an Object-Oriented Onto-Ethics

  2026cites this paper
• Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs

  2026cites this paper
• Heterogeneous-Effect Causal Graph Diffusion Network for sustainable regional economic upgrading

  2026cites this paper
• FAIR: A Design Theory for Artificial Intelligence Fairness

  2026cites this paper
• A pipeline for enabling path-specific causal fairness in observational health data

  2026cites this paper
• Uncovering algorithmic inequity: a conditional mutual information framework for detecting and mitigating hidden discrimination

  2026cites this paper
• CausalWrap: Model-Agnostic Causal Constraint Wrappers for Tabular Synthetic Data

  2026cites this paper
• SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition

  2026cites this paper
• Measures of classification bias derived from sample size analysis

  2026cites this paper
• Trade-offs between fairness and performance in educational AI: Analyzing post-processing bias mitigation on the OULAD

  2026cites this paper
• Fair counterfactual explanation: application to education

  2026cites this paper
• Causally Disentangled Contrastive Learning for Multilingual Speaker Embeddings

  2026cites this paper
• Counterfactual Spaces

  2026cites this paper
• Fairness risk and its privacy-enabled solution in AI-driven robotic applications

  2026cites this paper
• Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations

  2026cites this paper
• FATe of Bots: Ethical Considerations of Social Bot Detection

  2026cites this paper
• Trustworthy AI for medical decisions: Adversarially robust and fair machine learning prediction for Parkinson's disease.

  2026cites this paper
• The Development of a Large Language Model-Powered Chatbot to Advance Fairness in Machine Learning

  2026cites this paper
• Integrating Multiscale Consistency and Enhanced Feature Interaction for Cross-View Geo-Localization

  2026cites this paper
• Empowering Affected Individuals to Shape AI Fairness Assessments: Processes, Criteria, and Tools

  2026cites this paper
• Explaining Group Recommendations via Counterfactuals

  2026cites this paper
• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos

  2026cites this paper
• Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation

  2026cites this paper
• Prune bias from the root: Bias removal and fairness estimation by pruning sensitive attributes in pre-trained DNN models

  2026cites this paper
• Causal Manifold Fairness: Enforcing Geometric Invariance in Representation Learning

  2026cites this paper
• Counterfactual Fairness with Graph Uncertainty

  2026influential citation
• Topology matters: achieving fairness in graph neural networks through heterophily propagation

  2026cites this paper
• Unravelling the (In)compatibility of Statistical-Parity and Equalized-Odds

  2026cites this paper
• Learning fair representations without labeling sensitive attribute via dynamic environment partitioning and invariant learning

  2026cites this paper
• Fairness via Fuzzy Systems: Analysis of Accuracy–Fairness Tradeoff by Multiobjective Fuzzy Genetics-Based Machine Learning

  2026cites this paper
• On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation

  2026influential citation
• Inter-group knowledge transfer and representation distillation for fair recommendation

  2026cites this paper
• Feature-Aware Test Generation for Deep Learning Models

  2026cites this paper
• Position: A Potential Outcomes Perspective on Pearl's Causal Hierarchy

  2026cites this paper
• Axiomatic Foundations of Counterfactual Explanations

  2026cites this paper
• Individual Fairness In Strategic Classification

  2026cites this paper
• Counterfactual Fairness Evaluation of LLM-Based Contact Center Agent Quality Assurance System

  2026cites this paper
• Artificial Intelligence in Sentencing: Evaluating Machine Learning Models for Sentencing Recommendations in the U.S.

  2026cites this paper
• Fairness-Optimized Dynamic Aggregation (FODA): A Novel Approach to Equitable Federated Learning in Heterogeneous Environments

  2026cites this paper
• Fairness as an invariant: Regulating adaptive AI via closed-loop ergodic control

  2026cites this paper
• Fairness under Graph Uncertainty: Achieving Interventional Fairness with Partially Known Causal Graphs over Clusters of Variables

  2026cites this paper
• Operationalizing Fairness: Post-Hoc Threshold Optimization Under Hard Resource Limits

  2026cites this paper
• Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Pooling

  2025cites this paper
• From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI

  2025cites this paper
• FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering

  2025cites this paper
• The hard proxy problem: proxies aren’t intentional; they’re intentional

  2025cites this paper
• FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge

  2025cites this paper
• Enforcing Fairness Where It Matters: An Approach Based on Difference-of-Convex Constraints

  2025cites this paper
• Marginal Fairness: Fair Decision-Making under Risk Measures

  2025cites this paper
• Discrimination in FinTech era: debiasing algorithm for fair lending practices

  2025cites this paper
• Causally Fair Node Classification on Non-IID Graph Data

  2025cites this paper
• Interdisciplinary Perspectives on the (Un)fairness of Artificial Intelligence

  2025cites this paper
• Laypeople's Attitudes Towards Fair, Affirmative, and Discriminatory Decision-Making Algorithms

  2025cites this paper
• Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization's Impact on ML Fairness

  2025cites this paper
• Towards Fair In-Context Learning with Tabular Foundation Models

  2025cites this paper
• FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation

  2025cites this paper
• Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals

  2025cites this paper
• Improving Fairness in LLMs Through Testing-Time Adversaries

  2025cites this paper
• AI-driven healthcare: Fairness in AI healthcare: A survey

  2025cites this paper
• Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems

  2025cites this paper
• Decision-centric fairness: Evaluation and optimization for resource allocation problems

  2025cites this paper
• AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis

  2025cites this paper
• Understanding heterogeneity in psychiatric disorders: A method for identifying subtypes and parsing comorbidity

  2025cites this paper
• Practitioners and Bias in Machine Learning: A Study

  2025influential citation
• Investigating User-Side Fairness in Outcome and Process for Multi-Type Sensitive Attributes in Recommendations

  2025influential citation
• Towards Fair AI: Mitigating Bias in Credit Decisions—A Systematic Literature Review

  2025cites this paper
• Local Statistical Parity for the Estimation of Fair Decision Trees

  2025cites this paper
• Counterfactual Fairness Evaluation of Machine Learning Models on Educational Datasets

  2025influential citation
• Dynamic Detection and Debias of Bayesian Network Classifier (3D-BN)

  2025cites this paper
• Fairness Challenges in the Design of Machine Learning Applications for Healthcare

  2025influential citation
• Fairness Is More Than Algorithms: Racial Disparities in Time-to-Recidivism

  2025cites this paper
• Towards fair AI: a review of bias and fairness in machine intelligence

  2025cites this paper
• Comparative assessment of fairness definitions and bias mitigation strategies in machine learning-based diagnosis of Alzheimer’s disease from MR images

  2025cites this paper
• A Flexible Fairness Framework with Surrogate Loss Reweighting for Addressing Sociodemographic Disparities

  2025cites this paper
• DeCaFlow: A Deconfounding Causal Generative Model

  2025influential citation
• A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination

  2025influential citation
• Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models

  2025cites this paper
• The Human Complimentary Usage of AI and ML for Fair and Unbiased Educational Assessments

  2025cites this paper
• CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

  2025cites this paper
• Am I Being Treated Fairly? A Conceptual Framework for Individuals to Ascertain Fairness

  2025cites this paper
• Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairness

  2025cites this paper
• FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk

  2025cites this paper
• The European Union Artificial Intelligence Act: Mitigating Discrimination In Artificial Intelligence Systems

  2025cites this paper
• Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information

  2025cites this paper
• Discrimination, artificial intelligence, and algorithmic decision-making

  2025cites this paper
• Fair Learning by Model Averaging

  2025cites this paper
• Towards a Better Understanding of Evaluating Trustworthiness in AI Systems

  2025cites this paper
• Towards Multi-stakeholder Evaluation of ML Models: A Crowdsourcing Study on Metric Preferences in Job-Matching System

  2025cites this paper
• Group-robust Machine Unlearning

  2025cites this paper
• Causal Feature Learning in the Social Sciences

  2025cites this paper
• Enforcing Consistency and Fairness in Multi-level Hierarchical Classification with a Mask-based Output Layer

  2025cites this paper
• Reducing AI bias in recruitment and selection: an integrative grounded approach

  2025cites this paper
• The epistemic dimension of algorithmic fairness: assessing its impact in innovation diffusion and fair policy making

  2025cites this paper
• BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models

  2025cites this paper
• Path-Specific Counterfactual Fairness via Dividend Correction

  2025cites this paper
• Discrimination-free Insurance Pricing with Privatized Sensitive Attributes

  2025cites this paper
• Automated Data Bias Mitigation Technique for Algorithmic Fairness

  2025cites this paper
• Testing for Causal Fairness

  2025cites this paper