Weakly Complete Event Logs in Process Mining

Abstract

Many information systems have a possibility to record their execution, and, in this way, to generate a trace about events describing the real system behaviour. From behaviour example records in traces of the event log, the α-algorithm automatically generates a process model that belongs to a subclass of Petri nets, known as workflow nets. One of the basic limiting assumptions of α-algorithm is that the event log needs to be complete. As a result of attempting to overcome the problem of completeness of the event log, we introduced the notion of weakly complete event logs, from which our modified technique and algorithm can produce the same result as the α-algorithm from complete logs on parallel processes. Thereby weakly complete logs can be significantly smaller than complete logs, considering the number of traces they consist of. Weakly complete logs were used for the realization of our idea of interactive parallel business process model generation.