Mathematical optimization modelling for group counterfactual explanations

Emilio Carrizosa, Jasone Ramírez-Ayerbe and Dolores Romero Morales

European Journal of Operational Research, 2024, vol. 319, issue 2, 399-412

Abstract: Counterfactual Analysis has shown to be a powerful tool in the burgeoning field of Explainable Artificial Intelligence. In Supervised Classification, this means associating with each record a so-called counterfactual explanation: an instance that is close to the record and whose probability of being classified in the opposite class by a given classifier is high. While the literature focuses on the problem of finding one counterfactual for one record, in this paper we take a stakeholder perspective, and we address the more general setting in which a group of counterfactual explanations is sought for a group of instances. We introduce some mathematical optimization models as illustration of each possible allocation rule between counterfactuals and instances, and we identify a number of research challenges for the Operations Research community.

Keywords: Machine learning; Interpretability; Mathematical optimization; Counterfactual explanations; Location analysis (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S037722172400002X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:ejores:v:319:y:2024:i:2:p:399-412

DOI: 10.1016/j.ejor.2024.01.002

Access Statistics for this article

European Journal of Operational Research is currently edited by Roman Slowinski, Jesus Artalejo, Jean-Charles. Billaut, Robert Dyson and Lorenzo Peccati

More articles in European Journal of Operational Research from Elsevier
Bibliographic data for series maintained by Catherine Liu ().