Legal requirements on explainability in machine learning

Adrien Bibal; Michael Lognoul; Alexandre De Streel; Benoît Frénay

doi:10.1007/s10506-020-09270-4

Legal requirements on explainability in machine learning

Adrien Bibal, Michael Lognoul, Alexandre De Streel, Benoît Frénay

Research output: Contribution to journal › Article › peer-review

367 Downloads (Pure)

Abstract

Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

Original language	English
Pages (from-to)	149-169
Number of pages	21
Journal	Artificial Intelligence & Law
Volume	29
Issue number	2
DOIs	https://doi.org/10.1007/s10506-020-09270-4 https://doi.org/10.1007/s10506-020-09270-4
Publication status	Published - Jun 2021

Keywords

Explainability
Interpretability
Law
Machine learning

Access to Document

8613Final published version, 849 KB

Cite this

@article{a4f5698841d84f7b922947abe7f51a2c,

title = "Legal requirements on explainability in machine learning",

abstract = "Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.",

keywords = "Explainability, Interpretability, Law, Machine learning",

author = "Adrien Bibal and Michael Lognoul and {De Streel}, Alexandre and Beno{\^i}t Fr{\'e}nay",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature B.V.",

year = "2021",

month = jun,

doi = "10.1007/s10506-020-09270-4",

language = "English",

volume = "29",

pages = "149--169",

journal = "Artificial Intelligence & Law",

issn = "1572-8382",

publisher = "Springer",

number = "2",

}

TY - JOUR

T1 - Legal requirements on explainability in machine learning

AU - Bibal, Adrien

AU - Lognoul, Michael

AU - De Streel, Alexandre

AU - Frénay, Benoît

PY - 2021/6

Y1 - 2021/6

N2 - Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

AB - Deep learning and other black-box models are becoming more and more popular today. Despite their high performance, they may not be accepted ethically or legally because of their lack of explainability. This paper presents the increasing number of legal requirements on machine learning model interpretability and explainability in the context of private and public decision making. It then explains how those legal requirements can be implemented into machine-learning models and concludes with a call for more inter-disciplinary research on explainability.

KW - Explainability

KW - Interpretability

KW - Law

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85088816026&partnerID=8YFLogxK

U2 - 10.1007/s10506-020-09270-4

DO - 10.1007/s10506-020-09270-4

M3 - Article

AN - SCOPUS:85088816026

SN - 1572-8382

VL - 29

SP - 149

EP - 169

JO - Artificial Intelligence & Law

JF - Artificial Intelligence & Law

IS - 2

ER -

Legal requirements on explainability in machine learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction

Cite this

Legal requirements on explainability in machine learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Student theses

Interpretability and Explainability in Machine Learning and their Application to Nonlinear Dimensionality Reduction

Cite this