Counterfactual Situation Testing: From Single to Multidimensional Discrimination
Not on the map. Why?
Abstract (arXiv)
We present counterfactual situation testing (CST), a causal data mining framework for detecting individual discrimination in a dataset of classifier decisions. CST answers the question ``what would have been the model outcome had the individual, or complainant, been of a different protected status?'' It extends the legally-grounded situation testing (ST) of Thanh et al. (2011) by operationalizing the notion of "fairness given the difference" via counterfactual reasoning. ST finds for each complainant similar protected and non-protected instances in the dataset; constructs, respectively, a control and test group; and compares the groups such that a difference in model outcomes implies a potential case of individual discrimination. CST, instead, avoids this idealized comparison by establishing the test group on the complainant's generated counterfactual, which reflects how the protected attribute when changed influences other seemingly neutral attributes of the complainant. Under CST we test for discrimination for each complainant by comparing similar individuals within the control and test group but dissimilar individuals across these groups. We consider single (e.g.,~gender) and multidimensional (e.g.,~gender and race) discrimination testing. For multidimensional discrimination we study multiple and intersectional discrimination and, as feared by legal scholars, find evidence that the former fails to account for the latter kind. Using a k-nearest neighbor implementation, we showcase CST on synthetic and real data. Experimental results show that CST uncovers a higher number of cases than ST, even when the model is counterfactually fair. CST, in fact, extends counterfactual fairness (CF) of Kusner et al. (2017) by equipping CF with confidence intervals, which we report for all experiments.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 32 of its 99 references that are in the map. First posted on arXiv 3 Feb 2025.
Builds on
32 of 99 references.
References · 32
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2017Counterfactual Fairnesscited by 804
- 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
- 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
- 2017Avoiding Discrimination through Causal Reasoningcited by 194
- 2018Path-Specific Counterfactual Fairnesscited by 181
- 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
- 2017Fairness Testing: Testing Software for Discriminationcited by 126
- 2019Towards a Critical Race Methodology in Algorithmic Fairnesscited by 125
- 2020Fair Regression with Wasserstein Barycenterscited by 100
- 2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
20 more
- 2019Machine Learning Methods Economists Should Know Aboutcited by 64
- 2022Fairness Testing: A Comprehensive Survey and Analysis of Trendscited by 62
- 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
- 2021The Use and Misuse of Counterfactuals in Ethical Machine Learningcited by 52
- 2019Discrimination in the Age of Algorithmscited by 51
- 2019FlipTest: Fairness Testing via Optimal Transportcited by 51
- 2020What's Sex Got To Do With Fair Machine Learning?cited by 38
- 2019The Sensitivity of Counterfactual Fairness to Unmeasured Confoundingcited by 35
- 2019Fair Data Adaptation with Quantile Preservationcited by 30
- 2019Encoding high-cardinality string categorical variablescited by 23
- 2018Automated Test Generation to Detect Individual Discrimination in AI Modelscited by 21
- 2019On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternativescited by 20
- 2023Multi-dimensional discrimination in Law and Machine Learning -- A comparative overviewcited by 15
- 2023Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Treecited by 14
- 2022The Long Arc of Fairness: Formalisations and Ethical Discoursecited by 13
- 2016Causal Inference for Social Discrimination Reasoningcited by 8
- 2023Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Differencecited by 8
- 2022What is Proxy Discrimination?cited by 7
- 2023Causal Fair Machine Learning via Rank-Preserving Interventional Distributionscited by 4
- 2024Mutatis Mutandis: Revisiting the Comparator in Discrimination Testingcited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.