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.
Bibliographical noteFunding Information:
The authors acknowledge all researchers who, through their work, have advocated and accelerated the adoption of (explainable) analytics in OR. The research of Roman Slowiński was supported by TAILOR, a project funded by the EU Horizon 2020 (research and innovation funding) programme (EC GA number 952215 ). Sebastián Maldonado, Carla Vairetti, and Richard Weber acknowledge financial support from FONDECYT Chile (Grants 1200221, 11200007, and 1221562), Fondef (IT23I0061), ANID PIA/PUENTE (AFB220003), and NeEDS, a project funded by the EU Horizon 2020 programme (EC GA number 822214 ).
© 2023 Elsevier B.V.
- Decision analysis
- Explainable artificial intelligence
- Interpretable machine learning