Project C02: Interactive learning of explainable, situation-adapted decision models

This is the icon of subproject C02
The icon shows 9 gray circles forming a square in a 3x3 grid. There is a blue line connecting some of these. The line starts in the left upper corner and ends in the right bottom corner.

Different strategies are necessary for different situations in machine-based decision-making. The strategy to be used depends, for instance, on the amount of time or information available to make the decision. In Project C02, researchers from the fields of computer science and economics are working on a method to adapt decision-making models to different situations in which experts and users are incorporated in the process of construction. The goal is to enable decision-makers to choose the most suitable model and to be able to retroactively check the decision made.

 

Research areas: Computer science, Economics

Project leaders

Prof. Dr. Eyke Hüllermeier

More about the person

Prof. Dr. Kirsten Thommes

More about the person

Staff

Stefan Heid, M.Sc.

More about the person

Jaroslaw Kornowicz, M.Sc.

More about the person

Support staff

Nils Bojack, Paderborn University

Julia Rustemeier, Paderborn University

Luca Manuel Siekermann, Paderborn University

Pub­lic­a­tions

The Role of Response Time for Algorithm Aversion in Fast and Slow Thinking Tasks

A. Lebedeva, J. Kornowicz, O. Lammert, J. Papenkordt, in: Artificial Intelligence in HCI, 2023.

DOI

Aggregating Human Domain Knowledge for Feature Ranking

J. Kornowicz, K. Thommes, Artificial Intelligence in HCI (2023).

DOI

Probabilistic Scoring Lists for Interpretable Machine Learning

J.M. Hanselle, J. Fürnkranz, E. Hüllermeier, in: Discovery Science, Springer Nature Switzerland, Cham, 2023.

DOI

Comparing Humans and Algorithms in Feature Ranking: A Case-Study in the Medical Domain

J.M. Hanselle, J. Kornowicz, S. Heid, K. Thommes, E. Hüllermeier, in: M. Leyer, J. Wichmann (Eds.), LWDA’23: Learning, Knowledge, Data, Analysis. , 2023.


Learning decision catalogues for situated decision making: The case of scoring systems

S. Heid, J.M. Hanselle, J. Fürnkranz, E. Hüllermeier, International Journal of Approximate Reasoning 171 (2024).

DOI

Towards a Computational Architecture for Co-Constructive Explainable Systems

M. Booshehri, H. Buschmeier, P. Cimiano, S. Kopp, J. Kornowicz, O. Lammert, M. Matarese, D. Mindlin, A.S. Robrecht, A.-L. Vollmer, P. Wagner, B. Wrede, in: Proceedings of the 2024 Workshop on Explainability Engineering, ACM, 2024, pp. 20–25.

DOI

Algorithm, Expert, or Both? Evaluating the Role of Feature Selection Methods on User Preferences and Reliance

J. Kornowicz, K. Thommes, ArXiv (2024).

DOI

Learning decision catalogues for situated decision making: The case of scoring systems

S. Heid, J.M. Hanselle, J. Fürnkranz, E. Hüllermeier, International Journal of Approximate Reasoning 171 (2024).

DOI

An Empirical Examination of the Evaluative AI Framework

J. Kornowicz, ArXiv (2024).

DOI

Human-AI Co-Construction of Interpretable Predictive Models: The Case of Scoring Systems

S. Heid, J. Kornowicz, J.M. Hanselle, E. Hüllermeier, K. Thommes, in: PROCEEDINGS 34. WORKSHOP COMPUTATIONAL INTELLIGENCE, 2024, p. 233.


Show all publications
C02.mp4
In this video the project leaders present their view of co-construction.