Simplifying Mined Process Models: An Approach Based on Unfoldings

Abstract

Process models discovered using process mining tend to be complex and have problems balancing between overfitting and underfitting. Overfitting models are not general enough while underfitting models allow for too much behavior. This paper presents a post-processing approach to simplify discovered process models while controlling the balance between overfitting and underfitting. The discovered process model, expressed in terms of a Petri net, is unfolded into a branching process using the event log. Subsequently, the resulting branching process is folded into a simpler process model capturing the desired behavior.