Challenges of Explaining the Behavior of Black-Box AI Systems
- Aleksandre Asatiani,
- Pekka Malo,
- Per Rådberg Nagbøl,
- Esko Penttinen,
- Tapani Rinta-Kahila,
- Antti Salovaara
- University of Gothenburg,
- Aalto University,
- The University of Queensland
Research Output:
Journal Article or Conference Article in Journal
Journal article
Peer-review
Open access
Publication Information
Output type
Research Output:
Journal Article or Conference Article in Journal
Journal article
Peer-reviewOriginal language
EnglishArticle number
7Pages from-to (Number of pages)
Pages 259-278Journal (Volume, Issue Number)
M I S Quarterly Executive (Volume 19, Issue 4)Publication milestones
- Published - 01/12/2020
Publication status
Published - 01/12/2020
ISSN
1540-1960Publication IDs
- Scopus: 85101862718
Abstract
There are many examples of problems resulting from inscrutable AI systems, so there is a growing need to be able to explain how such systems produce their outputs. Draw- ing on a case study at the Danish Business Authority, we provide a framework and recommendations for addressing the many challenges of explaining the behavior of black-box AI systems. Our findings will enable organizations to successfully develop and deploy AI systems without causing legal or ethical problems.
Publication metrics
PlumX, opens in new tab
Captures
108
Citations
124