Conformance Checking with Model Projections

Alignments are a well-established conformance checking technique that serve to reconcile system logs with normative process models. For processes involving multiple entities, such as objects and resources performing different tasks, the interaction of these entities must be taken into account in the alignments. In traditional approaches, it is achieved by considering a log event as matching a model event when all the entities registered in the logged event fully match the ones required by the model, thus considering events as unbreakable process atoms. We relax this requirement to deal with partial agreements between logged and modeled events and define relaxed alignments, aiming at maximizing the synchronized interactions between entities. Our approach is based on the use of projections of the log and model on individual objects, to deal with partial agreements. The optimality criterion is based on the cost function taking into account the deviating moves (events with non-matching event labels), the degree of (partial) event matches, and the correlations between non-matching parts of events involved in the process execution. Illustrating with a running example, we demonstrate that our approach yields alignments that better capture deviations in the context of complex, multi-object processes.