发表机构
SAP Signavio; University of Mannheim（SAP Signavio; 曼海姆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究首次系统评估多任务学习在预测性流程监控中的效果，发现其能显著提升下一活动预测并缓解类别不平衡，且任务平衡对低容量模型至关重要。
AI 中文摘要
预测性流程监控（PPM）预测正在进行的组织流程如何展开，使信息系统能够超越执行支持，迈向主动分析和监控。尽管深度学习已提高了PPM中的预测准确性，但大多数方法采用单任务学习（STL）设置，即为每个任务单独训练一个模型。这增加了维护工作量，并忽视了潜在的协同效应。多任务学习（MTL）在一个模型中联合学习多个预测目标，提供了一种有前景的替代方案，然而其在PPM中的有效性仍未得到充分探索。目前尚不清楚MTL是否以及在何种设置下优于STL，哪些预测任务从联合学习中获益最多，哪些任务组合特别具有协同效应，以及是否以及如何平衡任务。为填补这一空白，我们提出了首个针对PPM的MTL综合实证研究，评估了多种任务组合、神经架构和优化方法。总体而言，我们的结果将MTL定位为PPM的一种强大范式：我们观察到在下一活动预测方面有显著改进，并且使用MTL能固有地缓解类别不平衡问题，而任务平衡在低容量模型下尤为关键。
英文摘要
Predictive Process Monitoring (PPM) forecasts how ongoing organizational processes unfold, enabling information systems to move beyond execution support toward proactive analysis and monitoring. Although deep learning has improved prediction accuracy in PPM, most approaches follow a single-task learning (STL) setup, training a separate model per task. This increases maintenance effort and overlooks potential synergies. Multi-task learning (MTL), which jointly learns multiple prediction targets in one model, offers a promising alternative, yet its effectiveness in PPM remains underexplored. It remains unclear whether and under which settings MTL improves upon STL, which prediction tasks benefit most from joint learning, which task combinations are particularly synergistic, and if and how tasks should be balanced. To fill this gap, we present the first comprehensive empirical study of MTL for PPM, evaluating a variety of task combinations, neural architectures, and optimization methods. Overall, our results position MTL as a strong paradigm for PPM: we see substantial improvements in next-activity prediction and inherent mitigation of class imbalance using MTL, while task balancing is especially critical under low-capacity models.
CommentsAccepted for publication in the Proceedings of the 60th Hawaii International Conference on System Sciences (HICSS-60)
