Challenges of Explaining the Behavior of Black-Box AI Systems

Aalto University School Of Business (Finland) ,Aleksandre Asatiani,Aalto University School Of Business (Finland) ,Esko Penttinen,It University Of Copenhagen (Denmark) ,The University Of Queensland (Australia) ,Antti Salovaara,Pekka Malo,Aalto University School Of Arts, Design And Architecture (Finland) ,Tapani Rinta-Kahila,University Of Gothenburg (Sweden) ,Per Rådberg Nagbøl

doi:10.17705/2msqe.00037

Challenges of Explaining the Behavior of Black-Box AI Systems

Aalto University School Of Business (Finland) , Aleksandre Asatiani

Open Access

https://doi.org/10.17705/2msqe.00037

Copy DOI

Journal: MIS Quarterly Executive	Publication Date: Dec 1, 2020
Citations: 39

#AI Systems #Behavior Of Systems + Show 4 more

Abstract
Full-Text PDF
Similar Papers

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. Drawing 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.(1,2)

Full Text