Litcius/Paper detail

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

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

2023European Journal of Operational Research118 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Computer scienceNormativeAnalyticsData scienceManagement scienceData analysisBusiness intelligenceBig dataOperations researchKnowledge managementData miningPolitical scienceLawEngineeringEconomicsExplainable Artificial Intelligence (XAI)Forecasting Techniques and ApplicationsBig Data and Business Intelligence