Predictive Workflow Management.

Abstract

In this paper, we propose a new area for research in workflow management systems: the use of predictions in managing workflows. Predictions can be beneficial in making various decisions during workflow management such as: when to escalate? How much execution time to allow for each process step? What is a reasonable time for the whole process to complete? These questions are currently addressed by the business analyst in a static way for all process executions. We argue that by using predictions, workflow management systems can provide dynamic answers to these questions based on the current system state and past execution history. This should result in reduced operational costs and better system utilization, among other benefits. Keywords: Deadlines, Escalations, Escalation Cost, Prediction, Workflow, Workflow Management. 1 Introduction Today, organizations use workflow management systems (WFMSs) to streamline, automate, and manage business processes that depend on information system...

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 36 citations exist upstream.