Statistical Verification of Process Conformance Based on Log Equality Test

Abstract

In Big data and IoT environments, a huge-sized data is created as the result of process execution, some of which are generated by sensors. The main issue of such application has been to analyze the data in order to suggest enhancements to the process. Evaluation of the conformance of process models is of great importance in this regard. For this purpose, previous studies in process mining approach suggested conformance checking by measuring fitness that uses token replay and node-arc relations based on Petri net. However, fitness thus far has not considered statistical significance, but just offers a numeric ratio. We herein propose a statistical verification based on the Kolmogorov-Smirnov test to judge whether two different log data sets are following the same process model. Our method can also judge that a set of event log data is following a process model by playing out the model and generating event log data from the model. We also propose a new concept of 'Maximum Confidence Dependency' to solve the problem of the trade-off between model abstraction and process conformance. We expect that our method can be widely used in many applications which deal with business process enhancement by analyzing process model and execution log.