Challenges of explaining the behavior of black-box AI systems

Aleksandre Asatiani; Pekka Malo; Per Rådberg Nagbøl; Esko Penttinen; Tapani Rinta-Kahila; Antti Salovaara

doi:10.17705/2msqe.00037

Challenges of explaining the behavior of black-box AI systems

Aleksandre Asatiani^*, Pekka Malo, Per Rådberg Nagbøl, Esko Penttinen, Tapani Rinta-Kahila, Antti Salovaara

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific

36 Citations (Scopus)

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.

Original language	English
Article number	7
Pages (from-to)	259-278
Number of pages	20
Journal	MIS Quarterly Executive
Volume	19
Issue number	4
DOIs	https://doi.org/10.17705/2msqe.00037
Publication status	Published - Dec 2020
MoE publication type	B1 Non-refereed journal articles

Access to Document

10.17705/2msqe.00037

OpenUrl availability

Full text

Cite this

@article{98b33fd1859549de8a4c3569b8e9ad3a,

title = "Challenges of explaining the behavior of black-box AI systems",

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.",

author = "Aleksandre Asatiani and Pekka Malo and {R{\aa}dberg Nagb{\o}l}, Per and Esko Penttinen and Tapani Rinta-Kahila and Antti Salovaara",

year = "2020",

month = dec,

doi = "10.17705/2msqe.00037",

language = "English",

volume = "19",

pages = "259--278",

journal = "MIS Quarterly Executive",

issn = "1540-1960",

publisher = "Indiana University",

number = "4",

}

TY - JOUR

T1 - Challenges of explaining the behavior of black-box AI systems

AU - Asatiani, Aleksandre

AU - Malo, Pekka

AU - Rådberg Nagbøl, Per

AU - Penttinen, Esko

AU - Rinta-Kahila, Tapani

AU - Salovaara, Antti

PY - 2020/12

Y1 - 2020/12

N2 - 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.

AB - 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.

UR - https://aisel.aisnet.org/misqe/vol19/iss4/7/

U2 - 10.17705/2msqe.00037

DO - 10.17705/2msqe.00037

M3 - Article

SN - 1540-1960

VL - 19

SP - 259

EP - 278

JO - MIS Quarterly Executive

JF - MIS Quarterly Executive

IS - 4

M1 - 7

ER -

Challenges of explaining the behavior of black-box AI systems

Abstract

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this