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

TL;DR

This work introduces a transfer-learning–based approach to predictive process monitoring (PPM) designed for organizations with limited event data. The method transfers a base model and encoded representations (activity embeddings and relative timestamp encoding) from a source process to a target context, enabling effective PPM without target-domain fine-tuning. Evaluated in both intra- and inter-organizational IT service management use cases, the approach consistently outperforms traditional PPM baselines and demonstrates that pre-trained embeddings and cross-domain timestamp handling significantly improve cross-context transfer. The results emphasize practical adoption, scalability, and the potential for federated extensions to broaden access to PPM across organizations and processes.

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, which prevents 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. This technique is instantiated in both a real-life intra- and an inter-organizational use case, based on which numerical experiments are performed using event logs for IT service management processes. 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. The proposed technique allows organizations to benefit from transfer learning in intra- and inter-organizational settings by transferring resources such as pre-trained models within and across organizational boundaries.

Figures (8)

• Figure 1: Transfer process knowledge from source to target context in .
• Figure 2: Categories of zhuang2020comprehensive.
• Figure 3: Intra- and inter-organizational for .
• Figure 4: Overview of our -based technique. -specific and general resources that need to be transferred from the source context $S$ to the target context $T$ are colored blue and gray, respectively.
• Figure 5: Difference in embedding with model all-mpnet-base-v2 of activities in $L_S$ and $L_T$ for the intra-organizational use case.