Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.19016 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918130865930240 |
|---|---|
| author | Kurowski, Kelly Lu, Xixi Reijers, Hajo A |
| author_facet | Kurowski, Kelly Lu, Xixi Reijers, Hajo A |
| contents | Predictive Process Monitoring (PPM) aims to train models that forecast upcoming events in process executions. These predictions support early bottleneck detection, improved scheduling, proactive interventions, and timely communication with stakeholders. While existing research adopts a control-flow perspective, we investigate next-activity prediction from a resource-centric viewpoint, which offers additional benefits such as improved work organization, workload balancing, and capacity forecasting. Although resource information has been shown to enhance tasks such as process performance analysis, its role in next-activity prediction remains unexplored. In this study, we evaluate four prediction models and three encoding strategies across four real-life datasets. Compared to the baseline, our results show that LightGBM and Transformer models perform best with an encoding based on 2-gram activity transitions, while Random Forest benefits most from an encoding that combines 2-gram transitions and activity repetition features. This combined encoding also achieves the highest average accuracy. This resource-centric approach could enable smarter resource allocation, strategic workforce planning, and personalized employee support by analyzing individual behavior rather than case-level progression. The findings underscore the potential of resource-centric next-activity prediction, opening up new venues for research on PPM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Working My Way Back to You: Resource-Centric Next-Activity Prediction Kurowski, Kelly Lu, Xixi Reijers, Hajo A Machine Learning Predictive Process Monitoring (PPM) aims to train models that forecast upcoming events in process executions. These predictions support early bottleneck detection, improved scheduling, proactive interventions, and timely communication with stakeholders. While existing research adopts a control-flow perspective, we investigate next-activity prediction from a resource-centric viewpoint, which offers additional benefits such as improved work organization, workload balancing, and capacity forecasting. Although resource information has been shown to enhance tasks such as process performance analysis, its role in next-activity prediction remains unexplored. In this study, we evaluate four prediction models and three encoding strategies across four real-life datasets. Compared to the baseline, our results show that LightGBM and Transformer models perform best with an encoding based on 2-gram activity transitions, while Random Forest benefits most from an encoding that combines 2-gram transitions and activity repetition features. This combined encoding also achieves the highest average accuracy. This resource-centric approach could enable smarter resource allocation, strategic workforce planning, and personalized employee support by analyzing individual behavior rather than case-level progression. The findings underscore the potential of resource-centric next-activity prediction, opening up new venues for research on PPM. |
| title | Working My Way Back to You: Resource-Centric Next-Activity Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.19016 |