mlsanityData to 14 Oct 2026

Actionable Recourse in Linear Classification

arXiv 1809.06514 ↗First posted 18 Sep 2018stat.ML cs.LGcited by 328

Not on the map. Why?

Abstract (arXiv)

Machine learning models are increasingly used to automate decisions that affect humans - deciding who should receive a loan, a job interview, or a social service. In such applications, a person should have the ability to change the decision of a model. When a person is denied a loan by a credit score, for example, they should be able to alter its input variables in a way that guarantees approval. Otherwise, they will be denied the loan as long as the model is deployed. More importantly, they will lack the ability to influence a decision that affects their livelihood. In this paper, we frame these issues in terms of recourse, which we define as the ability of a person to change the decision of a model by altering actionable input variables (e.g., income vs. age or marital status). We present integer programming tools to ensure recourse in linear classification problems without interfering in model development. We demonstrate how our tools can inform stakeholders through experiments on credit scoring problems. Our results show that recourse can be significantly affected by standard practices in model development, and motivate the need to evaluate recourse in practice.

Key facts. Cited by 328 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 67; 2022: 54; 2023: 77; 2024: 55; 2025: 31; 2026: 44.

328 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  2. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 148
  3. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  4. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 126
  5. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 124
  6. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 123
  7. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  8. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  9. 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
  10. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 86
  11. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  12. 2021Leveraging Sparse Linear Layers for Debuggable Deep Networkscited by 82
38 more
  1. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  2. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  3. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
  4. 2021Strategic Classification Made Practicalcited by 59
  5. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  6. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  7. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  8. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  9. 2021Information Discrepancy in Strategic Learningcited by 48
  10. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  11. 2022Logic-Based Explainability in Machine Learningcited by 48
  12. 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
  13. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  14. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  15. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  16. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  17. 2021Fair Normalizing Flowscited by 38
  18. 2021Counterfactual Explanations in Sequential Decision Making Under Uncertaintycited by 37
  19. 2021Consistent Counterfactuals for Deep Modelscited by 37
  20. 2021Optimal Counterfactual Explanations in Tree Ensemblescited by 36
  21. 2021GeCo: Quality Counterfactual Explanations in Real Timecited by 32
  22. 2021Stateful Strategic Regressioncited by 32
  23. 2022DualCF: Efficient Model Extraction Attack from Counterfactual Explanationscited by 32
  24. 2022On the Privacy Risks of Algorithmic Recoursecited by 32
  25. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  26. 2022Causal Explanations and XAIcited by 30
  27. 2021How Well do Feature Visualizations Support Causal Understanding of CNN Activations?cited by 28
  28. 2022Fairness Transferability Subject to Bounded Distribution Shiftcited by 28
  29. 2022Understanding Instance-Level Impact of Fairness Constraintscited by 27
  30. 2021To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methodscited by 26
  31. 2021ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Modelscited by 25
  32. 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
  33. 2022Formalising the Robustness of Counterfactual Explanations for Neural Networkscited by 24
  34. 2021Counterfactual Explanations for Arbitrary Regression Modelscited by 22
  35. 2021Counterfactual Shapley Additive Explanationscited by 22
  36. 2023Plug-in Performative Optimizationcited by 22
  37. 2022Attribution-based Explanations that Provide Recourse Cannot be Robustcited by 20
  38. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20

50 most cited of 328 All 328 (JSON)