aiqbench analysis
This research introduces a neuro-symbolic framework that integrates decision mining into suffix prediction to address limitations of standard neural networks in handling rare process variants and short prefixes. By explicitly reasoning over mined decision rules, the approach enhances interpretability and accuracy for business process event forecasting without relying solely on dense event labels.
Decision-Aware Suffix Prediction and Reasoning of Business Processes
arXiv:2609.06169v1 Announce Type: new Abstract: Suffix prediction forecasts the remaining sequence of events of a running case until completion. Most approaches rely on neural networks trained on event logs, which, on average, perform well but struggle with short prefixes or targets belonging to a rare process variant. In such scenarios, the correct path may cross multiple branching decisions, determined primarily by case- and event-level attributes, a signal that NN-based suffix prediction models tend to underweight because they may heavily weight (dense) event labels. Decision mining extracts rules for such decisions from the event log, but has so far been applied only to post-hoc and what-if analysis, not suffix prediction. We therefore extend suffix prediction with decision mining, introducing a decision-aware suffix prediction framework, a neuro-symbolic approach that enables reasoning about predicted events via mined decision rules. Experiments on three of four event logs and three suffix predictors show that the framework can improve suffix prediction, especially for short prefixes but also for rare process variants, and adds intrinsic interpretability.
Abstract:Suffix prediction forecasts the remaining sequence of events of a running case until completion. Most approaches rely on neural networks trained on event logs, which, on average, perform well but struggle with short prefixes or targets belonging to a rare process variant. In such scenarios, the correct path may cross multiple branching decisions, determined primarily by case- and event-level attributes, a signal that NN-based suffix prediction models tend to underweight because they may heavily weight (dense) event labels. Decision mining extracts rules for such decisions from the event log, but has so far been applied only to post-hoc and what-if analysis, not suffix prediction. We therefore extend suffix prediction with decision mining, introducing a decision-aware suffix prediction framework, a neuro-symbolic approach that enables reasoning about predicted events via mined decision rules. Experiments on three of four event logs and three suffix predictors show that the framework can improve suffix prediction, especially for short prefixes but also for rare process variants, and adds intrinsic interpretability.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.06169 [cs.LG]
(or arXiv:2609.06169v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.06169 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 261 words
Related coverage
How GoFundMe became America’s backup plan
The Verge · Aug 24, 2026
Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC
Latent Space · Sep 16, 2026
A Red Line and Oversight Framework for Government AI Contracts
AI Alignment Forum · Jul 18, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026