Predictive Process Monitoring

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 9

All topics

Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction
Sep 21, 2026Fabian Spaeh, Jingxing Fang, Shandian Zhe +1Event Time Prediction Predictive Process Monitoring
Celonis
Complete Suffix Prediction for Recommendation via Latent Retrieval over Process Graphs
Sep 14, 2026Sarra Madad, Myriam Maumy, Fr{é}d{é}ric Bertrand +1Predictive Process Monitoring Process Mining
UTT, LIST3N - OPTI, QAD · LIST3N Lab, AI Lab · University of Technology of Troyes (UTT), QAD +11
Leveraging contextual events on structure-aware next activity prediction
Sep 8, 2026Alessandro Mele, Claudia Diamantini, Domenico PotenaPredictive Process Monitoring Process Mining
Department of Information Engineering, Polytechnic University of Marche, Ancona, Marche, Italy
IPM-FM: A Foundation Model with Consensus Feature Selection for Industrial Process Monitoring
Sep 8, 2026Liang Cao, Weide Liu, Yan Qin +3Predictive Process Monitoring Process Supervision
Department of Chemical and Biological Engineering University of British Columbia Vancouver, BC, Canada · School of Computing and Artificial Intelligence Jiangxi University of Finance and Economics Nanchang, China · School of Automation Chongqing University Chongqing, China +2
Revisiting Predictive Process Monitoring in the Age of Foundation Models: A Comparative Study of Sequence, Tabular, and LLM Approaches
Jul 30, 2026Lennart Fertig, Lukas Kirchdorfer, Tobias SesterhennTabular Foundation Models Predictive Process Monitoring
University of Mannheim, Mannheim, Germany · SAP Signavio, Walldorf, Germany · Technical University of Clausthal, Clausthal, Germany
Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoring
Jul 20, 2026Kseniya Sahatova, Rafael Seidi Oyamada, Xuefei Lu +1Feature Attribution Predictive Process Monitoring
SKEMA Business School, 92156 Suresnes, France · KU Leuven, B-3000 Leuven, Belgium
Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring
Jun 17, 2026Fang Wang, Ernesto DamianiPredictive Process Monitoring Process Mining
Department of Computer Science, University of Milan, Via Giovanni Celoria, 18, Milano 20133, MI, Italy
David vs. Goliath in Next Activity Prediction: Argmax vs. LSTM, Transformer, and LLM
Jun 14, 2026Hans Weytjens, Ingo WeberLLM Evaluation Predictive Process Monitoring
Technical University of Munich, School of CIT, Germany · Fraunhofer Gesellschaft, Munich, Germany
From Data Lifting to Continuous Risk Estimation: A Process-Aware Pipeline for Predictive Monitoring of Clinical Pathways
May 5, 2026Pasquale Ardimento, Mario Luca Bernardi, Marta Cimitile +1Predictive Process Monitoring Process Mining
Department of Informatics, University of Bari Aldo Moro, Bari, Italy · Department of Engineering, University of Sannio, Benevento, Italy · Department of Economy and Law, UnitelmaSapienza University, Rome, Italy

Sep 21, 2026, cs.LGJ/K move · Enter open · S save

Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction

Fabian Spaeh, Jingxing Fang, Shandian Zhe, Bin Shen

Celonis

Event Time Prediction Predictive Process Monitoring Multimodal Fusion

Open paper AskPDF arXiv

Event logs arise in a wide range of real-world processes, capturing not only event activities and timestamps but also multi-modal contextual information. Existing event-sequence models, including many temporal point process approaches, primarily model event activities and timestamps while overlooking heterogeneous context, such as numerical measurements, categorical attributes, textual descriptions, and metadata associated with individual events and entire traces. In this paper, we propose Universal Multi-Modal Traceformer (UMT), a unified framework for incorporating heterogeneous process context into next-event prediction. Built on a Transformer backbone, UMT introduces a universal feature encoder that maps diverse feature types into a shared representation space and handles contextual information at both the event and trace levels. UMT further develops a per-event Perceiver module that dynamically weights contextual features and adaptively integrates them into event-token representations. To accommodate the heavy-tailed and potentially multi-modal distribution of inter-arrival times, UMT represents each interval at multiple temporal scales and jointly predicts the corresponding scale-specific quantities. Experiments on 13 real-world event logs show that UMT improves both next-event activity and time prediction over existing approaches.

Momentum

Related topics

Latest papers 9