A social evaluation of the perceived goodness of explainability in machine learning. Issue 1 (2nd January 2022)

• Record Type: Journal Article
• Authors: Wanner, Jonas; Herm, Lukas-Valentin; Heinrich, Kai; Janiesch, Christian
• Is Part Of: Journal of Business Analytics. Volume 5:Issue 1(2022)
• Page Start: 29
• Page End: 50
• Publication Date: 2022-01-02
• Subjects: Machine learning -- explainable artificial intelligence -- explainability -- behavioural study -- social evaluation; Business intelligence -- Periodicals; Management -- Statistical methods -- Periodicals; Decision making -- Statistical methods -- Periodicals; 658.403
• DOI: 10.1080/2573234X.2021.1952913
• Languages: English
• ISSNs: 2573-234X

Abstract

ABSTRACT: Machine learning in decision support systems already outperforms pre-existing statistical methods. However, their predictions face challenges as calculations are often complex and not all model predictions are traceable. In fact, many well-performing models are black boxes to the user who– consequently– cannot interpret and understand the rationale behind a model's prediction. Explainable artificial intelligence has emerged as a field of study to counteract this. However, current research often neglects the human factor. Against this backdrop, we derived and examined factors that influence the goodness of a model's explainability in a social evaluation of end users. We implemented six common ML algorithms for four different benchmark datasets in a two-factor factorial design and asked potential end users to rate different factors in a survey. Our results show that the perceived goodness of explainability is moderated by the problem type and strongly correlates with trustworthiness as the most important factor.