From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse
Not on the map. Why?
Abstract (arXiv)
Algorithmic recourse aims to provide actionable recommendations that enable individuals to change unfavorable model outcomes, and prior work has extensively studied properties such as efficiency, robustness, and fairness. However, the role of personalization in recourse remains largely implicit and underexplored. While existing approaches incorporate elements of personalization through user interactions, they typically lack an explicit definition of personalization and do not systematically analyze its downstream effects on other recourse desiderata. In this paper, we formalize personalization as individual actionability, characterized along two dimensions: hard constraints that specify which features are individually actionable, and soft, individualized constraints that capture preferences over action values and costs. We operationalize these dimensions within the causal algorithmic recourse framework, adopting a pre-hoc user-prompting approach in which individuals express preferences via rankings or scores prior to the generation of any recourse recommendation. Through extensive empirical evaluation, we investigate how personalization interacts with key recourse desiderata, including validity, cost, and plausibility. Our results highlight important trade-offs: individual actionability constraints, particularly hard ones, can substantially degrade the plausibility and validity of recourse recommendations across amortized and non-amortized approaches. Notably, we also find that incorporating individual actionability can reveal disparities in the cost and plausibility of recourse actions across socio-demographic groups. These findings underscore the need for principled definitions, careful operationalization, and rigorous evaluation of personalization in algorithmic recourse.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 68 references that are in the map. First posted on arXiv 9 Apr 2026.
Builds on
41 of 68 references.
References · 41
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2014Certifying and removing disparate impactcited by 715
- 2017Masked Autoregressive Flow for Density Estimationcited by 684
- 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
- 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
- 2018Actionable Recourse in Linear Classificationcited by 328
- 2015Strategic Classificationcited by 257
- 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
- 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
- 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
29 more
- 2020Multi-Objective Counterfactual Explanationscited by 157
- 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
- 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 144
- 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
- 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 131
- 2019Efficient Search for Diverse Coherent Explanationscited by 111
- 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
- 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
- 2020On the Fairness of Causal Algorithmic Recoursecited by 70
- 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
- 2023Causal normalizing flows: from theory to practicecited by 51
- 2019On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learningcited by 49
- 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
- 2022On the Privacy Risks of Algorithmic Recoursecited by 32
- 2021Amortized Generation of Sequential Algorithmic Recourses for Black-box Modelscited by 24
- 2021Directive Explanations for Actionable Explainability in Machine Learning Applicationscited by 14
- 2023Setting the Right Expectations: Algorithmic Recourse Over Timecited by 13
- 2021Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functionscited by 10
- 2022Personalized Algorithmic Recourse with Preference Elicitationcited by 9
- 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
- 2024Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunitycited by 9
- 2022Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesiscited by 8
- 2024Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Explorationcited by 8
- 2024Time Can Invalidate Algorithmic Recoursecited by 8
- 2024Feature Responsiveness Scores: Model-Agnostic Explanations for Recoursecited by 8
- 2023Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbationscited by 6
- 2025Reinforcement Learning for Durable Algorithmic Recoursecited by 3
- 2023Towards User Guided Actionable Recoursecited by 1
- 2025Fair and Actionable Causal Prescription Rulesetcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.