Explainable AI for Operational Research: A Defining Framework, Methods, Applications, and a Research Agenda
Fiche du document
1 septembre 2023
- ISIDORE Id: 10670/1.e9c589...
- hal: hal-04219546
- doi: 10.1016/j.ejor.2023.09.026
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.ejor.2023.09.026
Ce document est lié à :
info:eu-repo/grantAgreement//952215/EU/Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization/TAILOR
Ce document est lié à :
info:eu-repo/grantAgreement//EC GA number 822214/EU/NeEDS – Network of European Data Scientists - A Research and Innovation Staff Exchange (RISE) project under the Marie Skłodowska-Curie Program/NeEDS
info:eu-repo/semantics/OpenAccess
Mots-clés
Decision analysis XAI explainable artificial intelligence interpretable machine learning XAIORSujets proches
Instruction and study--Methods Scientific research Science research Science--Research Operational analysis Operational research Instruction and study--MethodsCiter ce document
Koen W. de Bock et al., « Explainable AI for Operational Research: A Defining Framework, Methods, Applications, and a Research Agenda », HAL SHS (Sciences de l’Homme et de la Société), ID : 10.1016/j.ejor.2023.09.026
Métriques
Partage / Export
Résumé
The ability to understand and explain the outcomes of data analysis methods, with regard to aiding decision-making, has become a critical requirement for many applications. For example, in operational research domains, data analytics have long been promoted as a way to enhance decision-making. This study proposes a comprehensive, normative framework to define explainable artificial intelligence (XAI) for operational research (XAIOR) as a reconciliation of three subdimensions that constitute its requirements: performance, attributable, and responsible analytics. In turn, this article offers in-depth overviews of how XAIOR can be deployed through various methods with respect to distinct domains and applications. Finally, an agenda for future XAIOR research is defined.
