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

Per Rådberg Nagbøl, Oliver Müller

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

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.
OriginalsprogEngelsk
TitelEGOV-CeDEM-ePart 2020 : Proceedings of Ongoing Research, Practitioners, Workshops, Posters, and Projects of the International Conference EGOV-CeDEM-ePart 2020
RedaktørerShefali Virkar, Marijn Janssen, Ida Lindgren, Ulf Melin, Francesco Mureddu, Peter Parycek, Efthimios Tambouris, Gerhard Schwabe, Hans Jochen Scholl
Antal sider267
UdgivelsesstedSweden
ForlagCEUR Workshop Proceedings
Publikationsdato2020
Sider259
StatusUdgivet - 2020
BegivenhedIFIP EGOV-ePart-CeDEM conference - Linköping Univeristy, Linköping, Sverige
Varighed: 31 aug. 20202 sep. 2020
http://dgsociety.org/egov-2020/

Konference

KonferenceIFIP EGOV-ePart-CeDEM conference
LokationLinköping Univeristy
Land/OmrådeSverige
ByLinköping
Periode31/08/202002/09/2020
Internetadresse
NavnCEUR Workshop Proceedings
Vol/bind2797
ISSN1613-0073

Emneord

  • Machine Learning Evaluation
  • Government
  • Interpretability

Fingeraftryk

Dyk ned i forskningsemnerne om 'X-RAI: A Framework for the Transparent, Responsible, and Accurate Use of Machine Learning in the Public Sector'. Sammen danner de et unikt fingeraftryk.

Citationsformater