FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring (Forthcoming)

Möhrlein F, Käppel M, Neuberger J, Weinzierl S, Ackermann L, Matzner M, Jablonski S (2025)

Publication Language: English

Publication Type: Book chapter / Article in edited volumes

Publication year: 2025

Edited Volumes: Proceedings of the Best BPM Dissertation Award, Doctoral Consortium, and Demonstrations & Resources Forum co-located with 23rd International Conference on Business Process Management (BPM 2025)

Abstract

Sensitive attributes like gender or age can lead to unfair predictions in machine learning tasks such as predictive business process monitoring, particularly when used without considering context. We present FairLoop, a tool for human-guided bias mitigation in neural network-based prediction models. FairLoop distills decision trees from neural networks, allowing users to inspect and modify unfair decision logic, which is then used to fine-tune the original model towards fairer predictions. Compared to other approaches to fairness, FairLoop enables context-aware bias removal through human involvement, addressing the influence of sensitive attributes selectively rather than excluding them uniformly.

Authors with CRIS profile

Martin Käppel Lehrstuhl für Digital Industrial Service Systems

Involved external institutions

Universität Bayreuth DE Germany (DE) Hochschule für Angewandte Wissenschaften Hof DE Germany (DE)

How to cite

APA:

Möhrlein, F., Käppel, M., Neuberger, J., Weinzierl, S., Ackermann, L., Matzner, M., & Jablonski, S. (2025). FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring (Forthcoming). In Proceedings of the Best BPM Dissertation Award, Doctoral Consortium, and Demonstrations & Resources Forum co-located with 23rd International Conference on Business Process Management (BPM 2025)..

MLA:

Möhrlein, Felix, et al. "FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring (Forthcoming)." Proceedings of the Best BPM Dissertation Award, Doctoral Consortium, and Demonstrations & Resources Forum co-located with 23rd International Conference on Business Process Management (BPM 2025). 2025.

BibTeX: Download