Comparing multiple processes
Besides the techniques that discover and analyze a single process, process mining is able to break down the differences between various processes, for example, the process of students that passed the course versus the process of students that failed.
What is Comparative Process Mining?

Process mining techniques enable the analysis of a wide variety of processes using event data. For example, event logs can be used to automatically learn a process model (e.g., a Petri net or BPMN model). Next to the automated discovery of the real underlying process, there are process mining techniques to analyze bottlenecks, uncover hidden inefficiencies, check compliance, explain deviations, predict performance, and guide users towards “better” processes. However, existing techniques focus on the analysis of a single process rather than the comparison of different processes. Using process cubes, comparative process mining can be applied to analyze multiple processes at the same time.

Process Cube
A process cube represents multidimensional process mining. In a process cube, events are organized using different dimensions (e.g., case types, regions, subprocesses, departments, and time windows). The cells in such a process cube can be analyzed using process mining techniques by creating a sub-log per cell. The results of different cells can be compared. Note that a process cube does not need to be limited to a single process: All events recorded in an organization can be organized in a single cube.

Given a process cube with suitably chosen dimensions, it is possible to compare process mining results generated for an array of cells. Such a procedure is called comparative process mining. The goal is to highlight differences between cells. This includes comparisons such as cross-checking conformance or comparing models visually or overlay the models as is supported by several process mining tools.

READ MORE