Neuer Artikel im International Journal of Information Management erschienen
![International Journal of Information Management International Journal of Information Management](/storages/ec-cs/_processed_/b/4/csm_2022-06-17_IJIM_081b482455.jpg)
Stop Ordering Machine Learning Algorithms by their Explainability!
Der Artikel "Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability" wurde im renommierten International Journal of Information Management (IJIM) angenommen. Das IJIM hat einen Impact Factor von 18.958 und ist #1 gerankt in SJR für Management Information Systems & Information Systems and Management.
Im Artikel zeigt Prof. Janiesch mit seinen Ko-Autoren Lukas-Valentin Herm, Kai Heinrich und Jonas Wanner folgendes:
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.
Der Artikel ist Open Access. https://doi.org/10.1016/j.ijinfomgt.2022.102538