FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911125772173312 |
|---|---|
| author | Möhrlein, Felix Käppel, Martin Neuberger, Julian Weinzierl, Sven Ackermann, Lars Matzner, Martin Jablonski, Stefan |
| author_facet | Möhrlein, Felix Käppel, Martin Neuberger, Julian Weinzierl, Sven Ackermann, Lars Matzner, Martin Jablonski, Stefan |
| contents | 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 FairLoop1, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20021 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring Möhrlein, Felix Käppel, Martin Neuberger, Julian Weinzierl, Sven Ackermann, Lars Matzner, Martin Jablonski, Stefan Machine Learning 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 FairLoop1, 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. |
| title | FairLoop: Software Support for Human-Centric Fairness in Predictive Business Process Monitoring |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.20021 |