Abstrakt
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.
Originalsprog | Engelsk |
---|---|
Titel | EGOV-CeDEM-ePart 2020 : Proceedings of Ongoing Research, Practitioners, Workshops, Posters, and Projects of the International Conference EGOV-CeDEM-ePart 2020 |
Redaktører | Shefali Virkar, Marijn Janssen, Ida Lindgren, Ulf Melin, Francesco Mureddu, Peter Parycek, Efthimios Tambouris, Gerhard Schwabe, Hans Jochen Scholl |
Antal sider | 267 |
Udgivelsessted | Sweden |
Forlag | CEUR Workshop Proceedings |
Publikationsdato | 2020 |
Sider | 259 |
Status | Udgivet - 2020 |
Begivenhed | IFIP EGOV-ePart-CeDEM conference - Linköping Univeristy, Linköping, Sverige Varighed: 31 aug. 2020 → 2 sep. 2020 http://dgsociety.org/egov-2020/ |
Konference
Konference | IFIP EGOV-ePart-CeDEM conference |
---|---|
Lokation | Linköping Univeristy |
Land/Område | Sverige |
By | Linköping |
Periode | 31/08/2020 → 02/09/2020 |
Internetadresse |
Navn | CEUR Workshop Proceedings |
---|---|
Vol/bind | 2797 |
ISSN | 1613-0073 |