Abstract Nowadays, artificial intelligence (AI) systems make predictions in numerous high stakes domains, including credit-risk assessment and medical diagnostics. Consequently, AI systems increasingly affect humans, yet many state-of-the-art systems lack transparency and thus, deny the individual’s “right to explanation”. As a remedy, researchers and practitioners have developed explainable AI, which provides reasoning on how AI systems infer individual predictions. However, with recent legal initiatives demanding comprehensive explainability throughout the (development of an) AI system, we argue that the pre-processing stage has been unjustifiably neglected and should receive greater attention in current efforts to establish explainability. In this paper, we focus on introducing explainability to an integral part of the pre-processing stage: feature selection. Specifically, we build upon design science research to develop a design framework for explainable feature selection. We instantiate the design framework in a running software artifact and evaluate it in two focus group sessions. Our artifact helps organizations to persuasively justify feature selection to stakeholders and, thus, comply with upcoming AI legislation. We further provide researchers and practitioners with a design framework consisting of meta-requirements and design principles for explainable feature selection.


    Zugriff

    Zugriff über TIB


    Exportieren, teilen und zitieren



    Titel :

    Designing a feature selection method based on explainable artificial intelligence


    Beteiligte:
    Zacharias, Jan (Autor:in) / von Zahn, Moritz (Autor:in) / Chen, Johannes (Autor:in) / Hinz, Oliver (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    BKL:    83.72 Verkehrswirtschaft / 85.40 Marketing



    ONBOARD EXPLAINABLE ARTIFICIAL INTELLIGENCE

    Faggioli, Guglielmo / Varile, Mattia | TIBKAT | 2022


    Explainable and responsible artificial intelligence

    Meske, Christian / Abedin, Babak / Klier, Mathias et al. | Online Contents | 2022

    Freier Zugriff

    Explainable Artificial Intelligence for Aviation Safety Applications

    Saraf, Aditya P. / Chan, Kennis / Popish, Martin et al. | AIAA | 2020


    Explainable Artificial Intelligence Methodology for Handwritten Applications

    Whitten, Paul / Wolff, Francis / Papachristou, Chris | IEEE | 2021


    EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR AVIATION SAFETY APPLICATIONS

    Saraf, Aditya P. / Chan, Kennis / Popish, Martin et al. | TIBKAT | 2020