Predictive process monitoring for collaborative business processes: concepts and application
Abstract Predictive Process Monitoring (PPM), a subfield of Process Mining, leverages historical execution data and real-time observations to predict the future states or outcomes of ongoing business process instances. Existing techniques enable predictions, such as the next process activity or the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-06-01
|
| Series: | Discover Analytics |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44257-025-00031-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Predictive Process Monitoring (PPM), a subfield of Process Mining, leverages historical execution data and real-time observations to predict the future states or outcomes of ongoing business process instances. Existing techniques enable predictions, such as the next process activity or the completion time. These capabilities support proactive management by identifying potential deviations, violations, and delays, allowing organizations to implement preventive measures, such as reallocating resources. However, Process Mining research has predominantly focused on orchestration-type processes executed within a single organization (intra-organizational processes). Collaborative (inter-organizational) processes span multiple participant organizations and introduce additional complexity and challenges for their execution and analysis. Despite their significance, PPM for collaborative processes has received limited attention. This study addresses this gap by investigating PPM for collaborative processes. We identify predictions of particular relevance in collaborative environments, such as forecasting the following message exchange between participants. Furthermore, we propose adapting traditional PPM techniques designed for orchestration-type processes to suit the unique requirements of collaborative processes. This adaptation is implemented by developing a tool, Predict-Collab, extending the ProcessTransformer, which we preliminarily assess to demonstrate its potential. |
|---|---|
| ISSN: | 2731-8117 |