Search papers, labs, and topics across Lattice.
This study systematically benchmarks predictive process monitoring (PPM) using three modeling paradigms: deep sequence models, tabular foundation models, and large language models (LLMs). The findings reveal that while sequence models excel in predicting the next activity, tabular models show competitive performance in temporal tasks, and LLMs generally underperform despite their higher resource requirements. This comparative analysis highlights the evolving landscape of PPM and questions the dominance of LLMs in this domain.
Sequence models outperform LLMs in predictive process monitoring, challenging the assumption that larger models always yield better results.
Predictive process monitoring (PPM) leverages event logs to forecast the future of running process instances, for instance, predicting the next activity, the remaining time until case completion, or the time to the next event. While PPM research in recent years has been dominated by deep sequence models trained from scratch, such as Long Short-Term Memory (LSTM) models, foundation-model approaches---particularly large language models (LLMs)---are increasingly explored for PPM. At the same time, tabular foundation models with in-context learning capabilities offer a promising alternative but have not yet been systematically benchmarked for PPM. Thus, it remains unclear whether classical sequence-based models remain competitive in this evolving landscape. This paper compares the three modeling paradigms both conceptually and empirically through a controlled benchmark across multiple datasets and prediction tasks. The results show that sequence models consistently perform best for next activity prediction, whereas tabular foundation models are competitive on temporal tasks, with LLMs usually lagging behind despite higher cost.
