Explainable AI for Operational Research: A defining framework, methods, applications, and a research agenda

Koen W. De Bock, Kristof Coussement, Arno De Caigny, Roman Slowinski, Bart Baesens, Robert N. Boute, Tsan-Ming Choi, Dursun Delen, Mathias Kraus, Stefan Lessmann, Sebastián Maldonado, David Martens, María Óskarsdóttir, Carla Vairetti, Wouter Verbeke, Richard Weber

Abstract: Highlights•We define and characterize Explainable AI for Operational Research (XAIOR).•3 subdimensions of XAIOR are performance, attributable, and responsible analytics.•Methods, algorithms, and applications of XAIOR in 6 major OR domains are reviewed.•We present an ambitious agenda for XAIOR research.