mlsanityData to 14 Oct 2026

Improvement-Focused Causal Recourse (ICR)

arXiv 2210.15709 ↗First posted 27 Oct 2022stat.ML cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Algorithmic recourse recommendations, such as Karimi et al.'s (2021) causal recourse (CR), inform stakeholders of how to act to revert unfavourable decisions. However, some actions lead to acceptance (i.e., revert the model's decision) but do not lead to improvement (i.e., may not revert the underlying real-world state). To recommend such actions is to recommend fooling the predictor. We introduce a novel method, Improvement-Focused Causal Recourse (ICR), which involves a conceptual shift: Firstly, we require ICR recommendations to guide towards improvement. Secondly, we do not tailor the recommendations to be accepted by a specific predictor. Instead, we leverage causal knowledge to design decision systems that predict accurately pre- and post-recourse. As a result, improvement guarantees translate into acceptance guarantees. We demonstrate that given correct causal knowledge, ICR, in contrast to existing approaches, guides towards both acceptance and improvement.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 38 of its 79 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

38 of 79 references.

References · 38

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  3. 2017Counterfactual Fairnesscited by 804
  4. 2018Pyro: Deep Universal Probabilistic Programmingcited by 380
  5. 2018Actionable Recourse in Linear Classificationcited by 328
  6. 2015Strategic Classificationcited by 257
  7. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  8. 2017Avoiding Discrimination through Causal Reasoningcited by 194
  9. 2020Fairness in Machine Learningcited by 194
  10. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 191
  11. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  12. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 172
26 more
  1. 2019Predictive Multiplicity in Classificationcited by 166
  2. 2020Multi-Objective Counterfactual Explanationscited by 157
  3. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 144
  4. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
  5. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  6. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  7. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  8. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  9. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  10. 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
  11. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  12. 2019Strategic Classification is Causal Modeling in Disguisecited by 92
  13. 2017Causal Structure Learningcited by 84
  14. 2020On Counterfactual Explanations under Predictive Multiplicitycited by 74
  15. 2020Causal Strategic Linear Regressioncited by 65
  16. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  17. 2018Conditional Density Estimation with Bayesian Normalising Flowscited by 54
  18. 2020Survey on Causal-based Machine Learning Fairness Notionscited by 54
  19. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
  20. 2015Interpretable Classification Models for Recidivism Predictioncited by 44
  21. 2020Decisions, Counterfactual Explanations and Strategic Behaviorcited by 44
  22. 2020The Intriguing Relation Between Counterfactual Explanations and Adversarial Examplescited by 44
  23. 2020Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shiftscited by 36
  24. 2019Stabilizing Variable Selection and Regressioncited by 31
  25. 2020Linear Classifiers that Encourage Constructive Adaptationcited by 16
  26. 2020Gaming Helps! Learning from Strategic Interactions in Natural Dynamicscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 6; 2025: 4; 2026: 4.

20 papers.

Sort:

By area:

  1. 2023Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Researchcited by 22
  2. 2023Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Modelcited by 14
  3. 2023The Risks of Recourse in Binary Classificationcited by 8
  4. 2025Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertaintycited by 8
  5. 2025Performative Validity of Recourse Explanationscited by 8
  6. 2024Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Marketscited by 6
  7. 2024CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forestscited by 5
  8. 2023Prediction without Preclusion: Recourse Verification with Reachable Setscited by 4
  9. 2024Trustworthy Actionable Perturbationscited by 3
  10. 2025Optimal Robust Recourse with Lp-Bounded Model Changecited by 3
  11. 2025Reinforcement Learning for Durable Algorithmic Recoursecited by 3
  12. 2023counterfactuals: An R Package for Counterfactual Explanation Methodscited by 2
8 more
  1. 2023The Importance of Time in Causal Algorithmic Recoursecited by 2
  2. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  3. 2024SIDEs: Separating Idealization from Deceptive Explanations in xAIcited by 2
  4. 2024S-CFE: Simple Counterfactual Explanationscited by 1
  5. 2026The Role of Causality in Algorithmic Recoursecited by 1
  6. 2026cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Contextcited by 0
  7. 2026We Need Explanation Cards to Connect Explanation Algorithms to the Real Worldcited by 0
  8. 2026Algorithmic Recourse Under Competitioncited by 0