To content
Department of Computer Science
Research

New article published in the International Journal of Information Management

International Journal of Information Management © Elsevier (2022)
Stop Ordering Machine Learning Algorithms by their Explainability!

The article "Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability" was published in the renowned International Journal of Information Management (IJIM). IJIM has an Impact Factor of 18.958 and is ranked #1 in SJR fpr Management Information Systems & Information Systems and Management.

In the article, Prof. Janiesch with his co-authors Lukas-Valentin Herm, Kai Heinrich, and Jonas Wanner the following:

Explaining AI system decision models to users is becoming ever more important. But mathematical and programmatic considerations do not suffice to scrutinize applications with humans. We show that we should neither simplify the tradeoff between performance and explainability as continuous nor that the data-driven interpretability of algorithms entails algorithm explainability towards end users. Rather, we show that there are currently three groups of algorithm explainability somewhat distinct in performance capabilities. Hence, we say: Stop Ordering Machine Learning Algorithms by their Explainability.

The article is available as open access. https://doi.org/10.1016/j.ijinfomgt.2022.102538