ITU

X-RAI: A Framework for the Transparent, Responsible, and Accurate Use of Machine Learning in the Public Sector

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

This paper reports on an Action Design Research project taking place in the Danish Business Authority focusing on quality assurance and evaluation of machine learning models in production. The design artifact is a Framework (X-RAI) which stands for Transparency (X-Ray), Responsible(R), and explainable (X-AI). X-RAI consist of four sub-frameworks: the Model Impact and Clarification Framework, Evaluation Plan Framework, Evaluation Support Framework, and Retraining Execution Framework for machine learning that builds upon the theory of interpretable AI and practical experiences tested on nine different machine learning models used by the Danish Business Authority.
Original languageEnglish
Title of host publicationEGOV-CeDEM-ePart 2020 : Proceedings of Ongoing Research, Practitioners, Workshops, Posters, and Projects of the International Conference EGOV-CeDEM-ePart 2020
EditorsShefali Virkar, Marijn Janssen, Ida Lindgren, Ulf Melin, Francesco Mureddu, Peter Parycek, Efthimios Tambouris, Gerhard Schwabe, Hans Jochen Scholl
Number of pages267
Place of PublicationSweden
PublisherCEUR Workshop Proceedings
Publication date2020
Pages259
Publication statusPublished - 2020
EventIFIP EGOV-ePart-CeDEM conference - Linköping Univeristy, Linköping, Sweden
Duration: 31 Aug 20202 Sep 2020
http://dgsociety.org/egov-2020/

Conference

ConferenceIFIP EGOV-ePart-CeDEM conference
LocationLinköping Univeristy
LandSweden
ByLinköping
Periode31/08/202002/09/2020
Internetadresse
SeriesCEUR Workshop Proceedings
Volume2797
ISSN1613-0073
Close

    Research areas

  • Machine Learning Evaluation, Government, Interpretability

Downloads

No data available

ID: 85594404