Junior Professorship for AI-Based Decision Support

In the summer term 2025 we will  offer the lecture  AI-based Decision Support II as well as the Scientific Project: Applications of Artificial Intelligence.  As every term, we also have openings for master thesis topics (please check out the dealines!).

Application schedule:

• AIbDS II will be available for enrollment mid March - just visit the e-learning site here.
• For the Scientific project, you have to use the central application process provided by the faculty and the dean of study affairs. You will be added to the e-learning course automatically by us. A mail will be sent out prior to the enrollment (the date of the mail depends on your priority I or II) to confirm you are in the seminar
• For the master's application, please refer to the info page linked above

Together with colleagues from JMU Würzburg, we published a paper on the trade-off between explainability and accuracy in ML research.

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 here and open access in the International Journal of Information Management, #1 journal in SJR for Management Information Systems & Information Systems and Management. 

Artificial intelligence technology has started to shape how decisions are being taken and how intelligent information systems are being implemented today. However, artificial intelligence should not be considered as an abstract system property, but researchers and practitioners must also understand its inner workings as it affects many socio-technical issues downstream.

In our Electronic Markets fundamentals article “Machine Learning and Deep Learning”, together with co-authors Christian Janiesch and Kai Heinrich, we distinguish approaches for shallow machine learning and deep learning and explain the process of analytical model building from a more technical information systems perspective. Further, we detail four overarching challenges that research and practice will have to manage going forward.

The article aims to be a terminological baseline, gentle introduction and pointer to relevant work, as well as a motivator to approach said challenges.

The article is open access and available at: https://link.springer.com/article/10.1007%2Fs12525-021-00475-2

Together with colleagues from Würzburg, FAU and KIT we published two papers at the ECIS 2021 conference, which was held virtually in June. 

The first paper, which was submitted in a joint effort by colleagues from the KIT (Jannis Walk, Niklas Kühl and Michael Vössing) and FAU (Patrick Zschech) proposes Design Principals and testable proposition for Computer-Vision-based Hybrid Intelligence Systems. Besides technical aspects, we also focused on the often neglected socio-technical facets, such as trust, control, and autonomy.

The paper is available here: https://aisel.aisnet.org/ecis2021_rp/127/

The second paper that was submitted together with colleauges from the JMU Würzburg (Jonas Wanner, Laurell Popp, Kevin Fuchs, Kevin Fuchs and Christian Janiesch) explores adoption barriers for AI-based systems in the context of predictive maintenance.

The paper is available here: https://aisel.aisnet.org/ecis2021_rip/40/