A Multi-Task Learning Framework for Multi-View Predictive Business Process Monitoring

Predictive business process monitoring aims to forecast the future behaviors of ongoing process instances by analyzing historical event logs. Previous studies in this field have predominantly focused on one specific task, that is, to predict the next activity, the next resource that executes the next activity, the remaining execution time, etc., which ignore the mutual effects among various tasks. In this article, a framework that simultaneously performs multiple prediction tasks is proposed, which provides decision-makers with more comprehensive information and better adapts to complex business scenarios. Specifically, multi-view frequent patterns are firstly conducted from various perspectives to uncover explicit features of different prediction tasks, which serve as additional input for the prediction. Then, a multi-task learning model is designed to learn the implicit characteristics and relations among different prediction tasks as well as obtain accurate prediction results. Experiments on five real-life datasets prove that the proposed method outperforms state-of-the-art methods, and soft parameter sharing in multi-task learning is more effective than hard parameter sharing for PBPM tasks.