Challenges Towards Production-Ready Explainable Machine Learning

Veiber, Lisa; Allix, Kevin; Arslan, Yusuf; Bissyande, Tegawendé François D Assise; Klein, Jacques

Reference : Challenges Towards Production-Ready Explainable Machine Learning


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/44318

Title :	Challenges Towards Production-Ready Explainable Machine Learning
Language :	English
Author, co-author :	Veiber, Lisa [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Allix, Kevin [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Computer Science and Communications Research Unit (CSC) >]
	Arslan, Yusuf [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Bissyande, Tegawendé François D Assise [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Klein, Jacques [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Computer Science and Communications Research Unit (CSC) >]
Publication date :	Jul-2020
Main document title :	Proceedings of the 2020 USENIX Conference on Operational Machine Learning (OpML 20)
Author, co-author :	Veiber, Lisa
	Allix, Kevin
	Arslan, Yusuf
	Bissyande, Tegawendé François D Assise
	Klein, Jacques
Publisher :	USENIX Association
Peer reviewed :	Yes
Audience :	International
ISBN :	978-1-939133-15-1
Event name :	2020 USENIX Conference on Operational Machine Learning
Event date :	28-07-2020 to 07-08-2020
Event organizer :	USENIX
Event country :	CA
Keywords :	[en] machine learning ; explanations
Abstract :	[en] Machine Learning (ML) is increasingly prominent in or- ganizations. While those algorithms can provide near perfect accuracy, their decision-making process remains opaque. In a context of accelerating regulation in Artificial Intelligence (AI) and deepening user awareness, explainability has become a priority notably in critical healthcare and financial environ- ments. The various frameworks developed often overlook their integration into operational applications as discovered with our industrial partner. In this paper, explainability in ML and its relevance to our industrial partner is presented. We then dis- cuss the main challenges to the integration of ex- plainability frameworks in production we have faced. Finally, we provide recommendations given those challenges.
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/10993/44318
Other URL :	https://www.usenix.org/conference/opml20/presentation/veiber

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	AAA_opml20_paper_veiber.pdf		Publisher postprint	327.52 kB	View/Open

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices