A social evaluation of the perceived goodness of explainability in machine learning

Jonas Wanner, Lukas-Valentin Herm, Kai Heinrich and Christian Janiesch

Journal of Business Analytics, 2022, vol. 5, issue 1, 29-50

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.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/2573234X.2021.1952913 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:29-50

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tjba20

DOI: 10.1080/2573234X.2021.1952913

Access Statistics for this article

Journal of Business Analytics is currently edited by Dursan Delen

More articles in Journal of Business Analytics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().