Explainable AI for operational research: a defining framework, methods, applications, and a research agenda
Explainable AI for operational research: a defining framework, methods, applications, and a research agenda
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.
Decision analysis, Explainable artificial intelligence, Interpretable machine learning, XAI, XAIOR
De Bock, Koen W.
14190876-810c-453a-a9c6-cb11f8518e11
Coussement, Kristof
8b0a5cd9-9577-4732-a624-696a7037999a
Caigny, Arno De
2974a61e-a8f2-4ec6-a195-e1c90957cdce
Słowiński, Roman
83d7effc-b48c-4b91-a4b3-e86a5282d0a4
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Boute, Robert N.
4a9872d0-1c51-4a6d-ac90-0f01b9c8d628
Choi, Tsan-Ming
594d42c1-0264-4e78-afc3-aa6076284cf4
Delen, Dursun
c6e77fdb-4c7f-485b-861d-b4f18e66269a
Kraus, Mathias
235fb114-c2cb-4287-a8b8-cd3d82151db1
Lessmann, Stefan
3b9f8133-67bb-4bcc-9183-e1a5db294b01
Maldonado, Sebastián
9e5fb121-d905-4337-beb3-bba6f7da9ae2
Martens, David
42e7e141-fb3d-4ead-8e3a-96b39bab65f9
Óskarsdóttir, María
1622b6dd-5d25-4228-9418-a1729e9577e0
Vairetti, Carla
8bc5cd31-a76f-4888-bb09-f34e1b0df319
Verbeke, Wouter
57c0d98a-130a-4202-b6dd-cdc6914f4732
Weber, Richard
da9918d6-bc84-4c98-8ffe-2aaf7b58cf1b
De Bock, Koen W.
14190876-810c-453a-a9c6-cb11f8518e11
Coussement, Kristof
8b0a5cd9-9577-4732-a624-696a7037999a
Caigny, Arno De
2974a61e-a8f2-4ec6-a195-e1c90957cdce
Słowiński, Roman
83d7effc-b48c-4b91-a4b3-e86a5282d0a4
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Boute, Robert N.
4a9872d0-1c51-4a6d-ac90-0f01b9c8d628
Choi, Tsan-Ming
594d42c1-0264-4e78-afc3-aa6076284cf4
Delen, Dursun
c6e77fdb-4c7f-485b-861d-b4f18e66269a
Kraus, Mathias
235fb114-c2cb-4287-a8b8-cd3d82151db1
Lessmann, Stefan
3b9f8133-67bb-4bcc-9183-e1a5db294b01
Maldonado, Sebastián
9e5fb121-d905-4337-beb3-bba6f7da9ae2
Martens, David
42e7e141-fb3d-4ead-8e3a-96b39bab65f9
Óskarsdóttir, María
1622b6dd-5d25-4228-9418-a1729e9577e0
Vairetti, Carla
8bc5cd31-a76f-4888-bb09-f34e1b0df319
Verbeke, Wouter
57c0d98a-130a-4202-b6dd-cdc6914f4732
Weber, Richard
da9918d6-bc84-4c98-8ffe-2aaf7b58cf1b
De Bock, Koen W., Coussement, Kristof, Caigny, Arno De, Słowiński, Roman, Baesens, Bart, Boute, Robert N., Choi, Tsan-Ming, Delen, Dursun, Kraus, Mathias, Lessmann, Stefan, Maldonado, Sebastián, Martens, David, Óskarsdóttir, María, Vairetti, Carla, Verbeke, Wouter and Weber, Richard
(2023)
Explainable AI for operational research: a defining framework, methods, applications, and a research agenda.
European Journal of Operational Research.
(doi:10.1016/j.ejor.2023.09.026).
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.
Text
1-s2.0-S0377221723007294-main
- Proof
More information
Accepted/In Press date: 19 September 2023
e-pub ahead of print date: 22 September 2023
Additional Information:
Funding 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 ).
Keywords:
Decision analysis, Explainable artificial intelligence, Interpretable machine learning, XAI, XAIOR
Identifiers
Local EPrints ID: 483940
URI: http://eprints.soton.ac.uk/id/eprint/483940
ISSN: 0377-2217
PURE UUID: 7cf6ac9b-20cb-44f4-8031-e0207059d1c9
Catalogue record
Date deposited: 07 Nov 2023 18:32
Last modified: 18 Mar 2024 02:59
Export record
Altmetrics
Contributors
Author:
Koen W. De Bock
Author:
Kristof Coussement
Author:
Arno De Caigny
Author:
Roman Słowiński
Author:
Robert N. Boute
Author:
Tsan-Ming Choi
Author:
Dursun Delen
Author:
Mathias Kraus
Author:
Stefan Lessmann
Author:
Sebastián Maldonado
Author:
David Martens
Author:
María Óskarsdóttir
Author:
Carla Vairetti
Author:
Wouter Verbeke
Author:
Richard Weber
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
