Stage-based Business Process Mining

Evidence-based BPM has gained significant momentum in recent years, thanks to the widespread adoption of enterprise systems that store detailed business process execution data in event logs. Techniques for analyzing business processes using event logs are termed “process mining” techniques. Their objective is to aid business analysts in improving business processes by learning knowledge from massive data. To date, techniques for process mining abound. For example, one can measure processing time and waiting time, diagnose process delays and quality issues, and replay an entire event log over a process model discovered from the log itself. However, these techniques often suffer from limited applicability, particularly when used on top of unpredictable processes such as patient treatment processes in healthcare as opposed to predictable processes such as a car manufacturing process. They failed to extract a highly fit process model, awkward in measuring process performance, and inaccurate in predictive monitoring. In addition, they are confused at how to divide the problem into sub-problems for better solutions. This research aims at designing a novel set of techniques based on a notion of business process stages which can improve over existing process mining techniques.