发表机构
Technical University of Munich（慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种结合决策挖掘的神经符号后缀预测框架，通过决策规则推理改进短前缀和稀有变体的预测，并增强可解释性。
AI 中文摘要
后缀预测用于预测运行中案例直到完成前的剩余事件序列。大多数方法依赖于在事件日志上训练的神经网络，这些网络在平均情况下表现良好，但在处理短前缀或属于稀有流程变体的目标时表现不佳。在此类场景中，正确路径可能跨越多个分支决策，这些决策主要由案例级和事件级属性决定，而基于神经网络的后缀预测模型往往低估了这一信号，因为它们可能过度加权（密集的）事件标签。决策挖掘从事件日志中提取此类决策的规则，但迄今为止仅应用于事后分析和假设分析，而非后缀预测。因此，我们将后缀预测与决策挖掘相结合，引入了一个决策感知的后缀预测框架，这是一种神经符号方法，能够通过挖掘出的决策规则对预测事件进行推理。在四个事件日志中的三个以及三个后缀预测器上的实验表明，该框架能够改进后缀预测，尤其是对于短前缀和稀有流程变体，并且增加了内在的可解释性。
英文摘要
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.
Comments18 pages, 4 figures, 1 table
