Explanatory Interactive Machine Learning

Nicolas Pfeuffer, Lorenz Baum, Wolfgang Stammer, Benjamin M. Abdel-Karim, Patrick Schramowski, Andreas M. Bucher, Christian Hügel, Gernot Rohde, Kristian Kersting and Oliver Hinz
Additional contact information
Nicolas Pfeuffer: Goethe University Frankfurt
Lorenz Baum: Goethe University Frankfurt
Wolfgang Stammer: Technical University of Darmstadt
Benjamin M. Abdel-Karim: Goethe University Frankfurt
Patrick Schramowski: Technical University of Darmstadt
Andreas M. Bucher: Hospital of the Goethe University Frankfurt
Christian Hügel: Hospital of the Goethe University Frankfurt
Gernot Rohde: Hospital of the Goethe University Frankfurt
Kristian Kersting: Technical University of Darmstadt

Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK, 2023, vol. 65, issue 6, No 4, 677-701

Abstract: Abstract The most promising standard machine learning methods can deliver highly accurate classification results, often outperforming standard white-box methods. However, it is hardly possible for humans to fully understand the rationale behind the black-box results, and thus, these powerful methods hamper the creation of new knowledge on the part of humans and the broader acceptance of this technology. Explainable Artificial Intelligence attempts to overcome this problem by making the results more interpretable, while Interactive Machine Learning integrates humans into the process of insight discovery. The paper builds on recent successes in combining these two cutting-edge technologies and proposes how Explanatory Interactive Machine Learning (XIL) is embedded in a generalizable Action Design Research (ADR) process – called XIL-ADR. This approach can be used to analyze data, inspect models, and iteratively improve them. The paper shows the application of this process using the diagnosis of viral pneumonia, e.g., Covid-19, as an illustrative example. By these means, the paper also illustrates how XIL-ADR can help identify shortcomings of standard machine learning projects, gain new insights on the part of the human user, and thereby can help to unlock the full potential of AI-based systems for organizations and research.

Keywords: Action design research; Data science; Explainable artificial intelligence; Interactive machine learning; Pneumonia; Corona virus (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12599-023-00806-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:binfse:v:65:y:2023:i:6:d:10.1007_s12599-023-00806-x

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/12599

DOI: 10.1007/s12599-023-00806-x

Access Statistics for this article

Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK is currently edited by Martin Bichler

More articles in Business & Information Systems Engineering: The International Journal of WIRTSCHAFTSINFORMATIK from Springer, Gesellschaft für Informatik e.V. (GI)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().