TY - JOUR
T1 - Explainable AI for Operational Research
T2 - a defining framework, methods, applications, and a research agenda
AU - De Bock, Koen W.
AU - Coussement, Kristof
AU - Caigny, Arno De
AU - Słowiński, Roman
AU - Baesens, Bart
AU - Boute, Robert N.
AU - Choi, Tsan Ming
AU - Delen, Dursun
AU - Kraus, Mathias
AU - Lessmann, Stefan
AU - Maldonado, Sebastián
AU - Martens, David
AU - Óskarsdóttir, María
AU - Vairetti, Carla
AU - Verbeke, Wouter
AU - Weber, Richard
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2024/9/1
Y1 - 2024/9/1
N2 - 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.
AB - 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.
KW - Decision analysis
KW - Explainable artificial intelligence
KW - Interpretable machine learning
KW - XAI
KW - XAIOR
UR - http://www.scopus.com/inward/record.url?scp=85173246691&partnerID=8YFLogxK
U2 - 10.1016/j.ejor.2023.09.026
DO - 10.1016/j.ejor.2023.09.026
M3 - Review article
AN - SCOPUS:85173246691
SN - 0377-2217
VL - 317
SP - 1
EP - 24
JO - European Journal of Operational Research
JF - European Journal of Operational Research
IS - 2
ER -