Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches | Lennart Fertig et al. | ResearchPod

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

Alex: Welcome to another episode of ResearchPod.

Sam: Today we're looking at a question that's become increasingly pressing in the world of data science. Businesses run on processes—supply chains, hospital admissions, loan approvals—and for years, researchers have built specialized software to predict what happens next in those processes. Now that large, general-purpose AI models are everywhere, the question is: should we replace those specialized tools with the new ones?

Alex: And I'm guessing the answer isn't a simple yes or no.

Sam: Not at all. The paper we're discussing, "Revisiting Predictive Process Monitoring in the Age of Foundation Models," puts three different types of models head-to-head on real business process data. The central puzzle is whether these newer, larger models actually outperform the older, purpose-built ones—or whether specialization still wins.

Alex: So what are the three types they're comparing?

Sam: Think of it like three different ways to learn a job. The first type is called a sequence model. Imagine a factory worker who has spent years on the same assembly line. They know exactly which step comes after which, because they've done it thousands of times. These models are trained from scratch on a specific process, and they develop a deep instinct for the order of events.

Alex: So they learn one process really well, but only that process.

Sam: Right. The second type is a Large Language Model—an LLM. Think of this as a very well-read assistant who has absorbed millions of documents. You give them a small amount of extra training on your specific process, and they use their broad general knowledge to guess what comes next. They haven't lived on your assembly line, but they've read about a lot of assembly lines.

Alex: And the third type?

Sam: These are called tabular foundation models. Rather than following the sequence of events like a story, they take a snapshot of the current moment—what step are we on, how much time has passed, what resources are involved—and use that snapshot to make a prediction. Where sequence models read the whole story of a process, tabular models read the current chapter summary.

Alex: So the researchers tested all three on real data. What were they actually trying to predict?

Sam: Three things: what the next step in a process will be, how long until that next step happens, and how long until the entire process finishes. These are called Predictive Process Monitoring tasks. The idea is that if you can spot a delay early, you can act before it becomes a real problem—an early warning system for operational bottlenecks.

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

Lennart Fertig, Lukas Kirchdorfer, Tobias Sesterhenn

Jul 30, 2026·5:46·arxiv·Original Paper

Predictive Process Monitoring (PPM)Sequence ModelsLarge Language Models (LLMs)Tabular Foundation ModelsBranching Complexity

Listen

6 min

Briefing

Research Overview

Predictive Process Monitoring (PPM) aims to forecast future process outcomes—such as the next activity, remaining time, or time until the next event—using historical event logs. While deep sequence models (like LSTMs) have long been the standard, the rise of foundation models has introduced new alternatives, including Large Language Models (LLMs) and tabular foundation models. This paper provides a systematic, controlled benchmark comparing these three paradigms to determine if classical sequence models remain the most effective approach.

Modeling Paradigms

The authors categorize PPM approaches into three distinct paradigms:

Classical Sequence Models: Models trained from scratch on event sequences, capturing temporal dependencies through recurrent or attention-based architectures.
LLM-based Approaches: Pretrained Transformer models adapted to process data via parameter-efficient fine-tuning (LoRA), treating event logs as structured sequences.
Tabular Foundation Models: Models that represent process prefixes as fixed-length feature vectors, utilizing in-context learning to make predictions without gradient-based training.

Key Findings

The empirical benchmark across five real-world event logs reveals that no single paradigm dominates every task. Sequence models (LSTM and Transformer) consistently achieve the highest accuracy for next-activity prediction, likely because they explicitly model the sequential trajectory of events. In contrast, tabular foundation models are highly competitive for temporal tasks (remaining time and next-event timing), often matching or exceeding sequence models. LLMs generally underperform compared to the other two paradigms while incurring significantly higher computational costs.

Why It Matters

This study clarifies the trade-offs between specialized sequence modeling and general-purpose foundation models in process mining. For practitioners, the results suggest that sequence models remain the robust choice for activity-based predictions, while tabular foundation models offer a viable, efficient alternative for temporal forecasting. The findings also highlight the limitations of applying LLMs to structured process data, suggesting that their general-purpose capabilities do not automatically translate to superior performance in process-specific tasks.

Key Terms and Definitions

Predictive Process Monitoring (PPM) — The application of machine learning to event logs to forecast future properties of running process instances.
Next Activity (NA) Prediction — A classification task that predicts the specific activity that will occur next in a process trace.
Remaining Time (RT) Prediction — A regression task that estimates the duration from the current point in a process until its final completion.
In-Context Learning — A capability of foundation models to perform tasks based on provided examples in the input, without requiring weight updates during inference.
Branching — A measure of process complexity referring to the number and distribution of possible successor activities at a given point in a process.

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.

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