A Conceptual Model for Implementing Explainable AI by Design: Results of an Empirical Study

Martin Van Den Berg*, Ouren Kuiper, Yvette Van Der Haas, Julie Gerlings, Danielle Sent, Stefan Leijnen

*Corresponding author af dette arbejde

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

108 Downloads (Pure)

Abstract

Artificial Intelligence (AI) offers organizations unprecedented opportunities. However, one of the risks of using AI is that its outcomes and inner workings are not intelligible. In industries where trust is critical, such as healthcare and finance, explainable AI (XAI) is a necessity. However, the implementation of XAI is not straightforward, as it requires addressing both technical and social aspects. Previous studies on XAI primarily focused on either technical or social aspects and lacked a practical perspective. This study aims to empirically examine the XAI related aspects faced by developers, users, and managers of AI systems during the development process of the AI system. To this end, a multiple case study was conducted in two Dutch financial services companies using four use cases. Our findings reveal a wide range of aspects that must be considered during XAI implementation, which we grouped and integrated into a conceptual model. This model helps practitioners to make informed decisions when developing XAI. We argue that the diversity of aspects to consider necessitates an XAI “by design” approach, especially in high-risk use cases in industries where the stakes are high such as finance, public services, and healthcare. As such, the conceptual model offers a taxonomy for method engineering of XAI related methods, techniques, and tools.
OriginalsprogEngelsk
TitelAugmenting Human Intellect : Proceedings of the 2nd International Conference on Hybrid Human-Artificial Intelligence. HHAI 2023
RedaktørerPaul Lukowicz, Sven Mayer, Janin Koch, John Shawe-Taylor, Ilaria Tiddi
Antal sider14
UdgivelsesstedAmsterdam
ForlagIOS Press
Publikationsdato2023
Sider60-73
ISBN (Trykt)9781643683942
ISBN (Elektronisk)9781643683959
DOI
StatusUdgivet - 2023
BegivenhedThe second International Conference on Hybrid Human-Artificial Intelligence - Munich, Tyskland
Varighed: 26 jun. 202330 jun. 2023
Konferencens nummer: 2
https://hhai-conference.org/2023/

Konference

KonferenceThe second International Conference on Hybrid Human-Artificial Intelligence
Nummer2
Land/OmrådeTyskland
ByMunich
Periode26/06/202330/06/2023
Internetadresse
Navn Frontiers in Artificial Intelligence and Applications
Vol/bind368
ISSN0922-6389

Emneord

  • Explainable AI (XAI)
  • Explainability
  • Financial services
  • Conceptual model

Citationsformater