From Source to Target: Leveraging Transfer Learning for Predictive Process Monitoring in Organizations

2025-08-11

AI Summary

Predictive Process Monitoring (PPM) is often hindered by scarce labeled event data from target processes, limiting its deployment in resource-constrained organizations. To address this, we propose a transfer learning–based cross-process PPM framework that enables knowledge transfer and model reuse by modeling semantic similarity between source and target processes. Our method jointly encodes process structural features and behavioral log representations. Evaluated on real-world IT service management scenarios, it demonstrates effective intra-organizational and cross-organizational transfer. Experiments show that, when target-process labeled data are reduced by 50%–90%, our approach maintains a 12.3%–28.7% improvement in prediction accuracy over conventional PPM and baseline transfer methods. This work extends the applicability of PPM to low-resource settings and provides a scalable, interpretable pathway for process knowledge reuse.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Intelligent Query Processing
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising

Abstract

Event logs reflect the behavior of business processes that are mapped in organizational information systems. Predictive process monitoring (PPM) transforms these data into value by creating process-related predictions that provide the insights required for proactive interventions at process runtime. Existing PPM techniques require sufficient amounts of event data or other relevant resources that might not be readily available, preventing some organizations from utilizing PPM. The transfer learning-based PPM technique presented in this paper allows organizations without suitable event data or other relevant resources to implement PPM for effective decision support. The technique is instantiated in two real-life use cases, based on which numerical experiments are performed using event logs for IT service management processes in an intra- and inter-organizational setting. The results of the experiments suggest that knowledge of one business process can be transferred to a similar business process in the same or a different organization to enable effective PPM in the target context. With the proposed technique, organizations can benefit from transfer learning in an intra- and inter-organizational setting, where resources like pre-trained models are transferred within and across organizational boundaries.

Problem

• Enables PPM for organizations lacking sufficient event data
• Transfers knowledge between similar processes across organizations
• Uses transfer learning for effective decision support in PPM

Innovation

• Transfer learning enables PPM without sufficient data
• Pre-trained models transfer within and across organizations
• Knowledge transfer between similar business processes