Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective
Annals of Operations Research · 2025-04 · 347 (2) · 991-1030
DOI: 10.1007/s10479-024-05943-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Annals of Operations Research, online erschienen am 03.04.2024. Verfasst von Nijat Mehdiyev und 2 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BMBF, Universität des Saarlandes.
Abstract (Originalsprache)
In the rapidly evolving landscape of manufacturing, the ability to make accurate predictions is crucial for optimizing processes. This study introduces a novel framework that combines predictive uncertainty with explanatory mechanisms to enhance decision-making in complex systems. The approach leverages Quantile Regression Forests for reliable predictive process monitoring and incorporates Shapley Additive Explanations (SHAP) to identify the drivers of predictive uncertainty. This dual-faceted strategy serves as a valuable tool for domain experts engaged in process planning activities. Supported by a real-world case study involving a medium-sized German manufacturing firm, the article validates the model’s effectiveness through rigorous evaluations, including sensitivity analyses and tests for statistical significance. By seamlessly integrating uncertainty quantification with explainable artificial intelligence, this research makes a novel contribution to the evolving discourse on intelligent decision-making in complex systems.
Förderung
- BMBF
- Universität des Saarlandes
Zitieren
APA
Mehdiyev, N., Majlatow, M., & Fettke, P. (2025). Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective. Annals of Operations Research, 347(2), 991-1030. https://doi.org/10.1007/s10479-024-05943-4
Vancouver
Mehdiyev N, Majlatow M, Fettke P. Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective. Annals of Operations Research. 2025;347(2):991-1030. doi:10.1007/s10479-024-05943-4
BibTeX
@article{Mehdiyev2025,
author = {Mehdiyev, Nijat and Majlatow, Maxim and Fettke, Peter},
title = {Quantifying and explaining machine learning uncertainty in predictive process monitoring: an operations research perspective},
journal = {Annals of Operations Research},
year = {2025},
volume = {347},
number = {2},
pages = {991--1030},
doi = {10.1007/s10479-024-05943-4}
}
EUVIMED