Paper Number
ECIS2025-1639
Paper Type
CRP
Abstract
In today’s volatile environment, organizations are constantly striving to optimize their processes to maintain competitive advantages. Thereby, process mining supports data-driven process optimization, for example, through prescriptive process monitoring. So far, prescriptive process monitoring mainly focuses on data from single organizations. However, there are often similar processes across several organizations with the same process goals but differing activities. This entails the potential for mutual learning from an interorganizational perspective. Yet, since process data contains sensitive information, data sovereignty represents a major requirement. Federated learning serves as a promising starting point to do so. Thus, following the design science paradigm, we developed, instantiated, and evaluated an approach for data-sovereign, interorganizational prescriptive process monitoring based on federated learning, providing a proof of concept and a foundation for future research.
Recommended Citation
Moder, Linda; Duda, Sebastian; Willburger, Lukas; Kraus Caballero, Roberto; Häckel, Björn; Röglinger, Maximilian; and Urbach, Nils, "TOWARD DATA-SOVEREIGN PRESCRIPTIVE PROCESS MONITORING – A FEDERATED LEARNING APPROACH" (2025). ECIS 2025 Proceedings. 2.
https://aisel.aisnet.org/ecis2025/bpm/bpm/2
TOWARD DATA-SOVEREIGN PRESCRIPTIVE PROCESS MONITORING – A FEDERATED LEARNING APPROACH
In today’s volatile environment, organizations are constantly striving to optimize their processes to maintain competitive advantages. Thereby, process mining supports data-driven process optimization, for example, through prescriptive process monitoring. So far, prescriptive process monitoring mainly focuses on data from single organizations. However, there are often similar processes across several organizations with the same process goals but differing activities. This entails the potential for mutual learning from an interorganizational perspective. Yet, since process data contains sensitive information, data sovereignty represents a major requirement. Federated learning serves as a promising starting point to do so. Thus, following the design science paradigm, we developed, instantiated, and evaluated an approach for data-sovereign, interorganizational prescriptive process monitoring based on federated learning, providing a proof of concept and a foundation for future research.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.