Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches

2026-07-30

AI Summary

In the context of the rise of foundation models, the relative performance of sequence models, tabular foundation models, and large language models (LLMs) in predictive process monitoring remains unclear. This study presents the first systematic and controlled benchmark comparison of these three modeling paradigms across multiple datasets and tasks, specifically evaluating their effectiveness in next-activity prediction and remaining time prediction. Experimental results demonstrate that sequence models—such as LSTMs—consistently achieve the best performance in activity prediction, while tabular foundation models show competitive results in time prediction. In contrast, LLMs generally underperform and incur substantially higher inference costs. These findings provide empirical evidence and practical guidance for model selection in predictive process monitoring applications.

Abstract

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.

Problem

• Predictive Process Monitoring
• Foundation Models
• Sequence Models
• Tabular Models
• Large Language Models

Innovation

• predictive process monitoring
• foundation models
• tabular models
• large language models
• sequence modeling