MC3G: Model Agnostic Causally Constrained Counterfactual Generation

Sopam Dasgupta, Sadaf MD Halim, Joaquín Arias, Elmer Salazar, Gopal Gupta
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:926-937, 2025.

Abstract

Machine learning models increasingly influence decisions in high-stakes settings such as finance, law and hiring, driving the need for transparent, interpretable outcomes. However, while explainable approaches can help understand the decisions being made, they may inadvertently reveal the underlying proprietary algorithm—an undesirable outcome for many practitioners. Consequently, it is crucial to balance meaningful transparency with a form of recourse that clarifies why a decision was made and offers actionable steps following which a favorable outcome can be obtained. Counterfactual explanations offer a powerful mechanism to address this need by showing how specific input changes lead to a more favorable prediction. We propose Model-Agnostic Causally Constrained Counterfactual Generation (MC3G), a novel framework that tackles limitations in the existing counterfactual methods. First, MC3G is model-agnostic: it approximates any black-box model using an explainable rule-based surrogate model. Second, this surrogate is used to generate counterfactuals that produce a favourable outcome for the original underlying black box model. Third, MC3G refines cost computation by excluding the “effort” associated with feature changes that occur automatically due to causal dependencies. By focusing only on user-initiated changes, MC3G provides a more realistic and fair representation of the effort needed to achieve a favourable outcome. We show that MC3G delivers more interpretable and actionable counterfactual recommendations compared to existing techniques all while having a lower cost. Our findings highlight MC3G’s potential to enhance transparency, accountability, and practical utility in decision-making processes that incorporate machine-learning approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-dasgupta25a, title = {MC3G: Model Agnostic Causally Constrained Counterfactual Generation}, author = {Dasgupta, Sopam and Halim, Sadaf MD and Arias, Joaqu\'{i}n and Salazar, Elmer and Gupta, Gopal}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {926--937}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/dasgupta25a/dasgupta25a.pdf}, url = {https://proceedings.mlr.press/v284/dasgupta25a.html}, abstract = {Machine learning models increasingly influence decisions in high-stakes settings such as finance, law and hiring, driving the need for transparent, interpretable outcomes. However, while explainable approaches can help understand the decisions being made, they may inadvertently reveal the underlying proprietary algorithm—an undesirable outcome for many practitioners. Consequently, it is crucial to balance meaningful transparency with a form of recourse that clarifies why a decision was made and offers actionable steps following which a favorable outcome can be obtained. Counterfactual explanations offer a powerful mechanism to address this need by showing how specific input changes lead to a more favorable prediction. We propose Model-Agnostic Causally Constrained Counterfactual Generation (MC3G), a novel framework that tackles limitations in the existing counterfactual methods. First, MC3G is model-agnostic: it approximates any black-box model using an explainable rule-based surrogate model. Second, this surrogate is used to generate counterfactuals that produce a favourable outcome for the original underlying black box model. Third, MC3G refines cost computation by excluding the “effort” associated with feature changes that occur automatically due to causal dependencies. By focusing only on user-initiated changes, MC3G provides a more realistic and fair representation of the effort needed to achieve a favourable outcome. We show that MC3G delivers more interpretable and actionable counterfactual recommendations compared to existing techniques all while having a lower cost. Our findings highlight MC3G’s potential to enhance transparency, accountability, and practical utility in decision-making processes that incorporate machine-learning approaches.} }
Endnote
%0 Conference Paper %T MC3G: Model Agnostic Causally Constrained Counterfactual Generation %A Sopam Dasgupta %A Sadaf MD Halim %A Joaquín Arias %A Elmer Salazar %A Gopal Gupta %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-dasgupta25a %I PMLR %P 926--937 %U https://proceedings.mlr.press/v284/dasgupta25a.html %V 284 %X Machine learning models increasingly influence decisions in high-stakes settings such as finance, law and hiring, driving the need for transparent, interpretable outcomes. However, while explainable approaches can help understand the decisions being made, they may inadvertently reveal the underlying proprietary algorithm—an undesirable outcome for many practitioners. Consequently, it is crucial to balance meaningful transparency with a form of recourse that clarifies why a decision was made and offers actionable steps following which a favorable outcome can be obtained. Counterfactual explanations offer a powerful mechanism to address this need by showing how specific input changes lead to a more favorable prediction. We propose Model-Agnostic Causally Constrained Counterfactual Generation (MC3G), a novel framework that tackles limitations in the existing counterfactual methods. First, MC3G is model-agnostic: it approximates any black-box model using an explainable rule-based surrogate model. Second, this surrogate is used to generate counterfactuals that produce a favourable outcome for the original underlying black box model. Third, MC3G refines cost computation by excluding the “effort” associated with feature changes that occur automatically due to causal dependencies. By focusing only on user-initiated changes, MC3G provides a more realistic and fair representation of the effort needed to achieve a favourable outcome. We show that MC3G delivers more interpretable and actionable counterfactual recommendations compared to existing techniques all while having a lower cost. Our findings highlight MC3G’s potential to enhance transparency, accountability, and practical utility in decision-making processes that incorporate machine-learning approaches.
APA
Dasgupta, S., Halim, S.M., Arias, J., Salazar, E. & Gupta, G.. (2025). MC3G: Model Agnostic Causally Constrained Counterfactual Generation. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:926-937 Available from https://proceedings.mlr.press/v284/dasgupta25a.html.

Related Material