Quantifying Conformance Between Object-Centric Event Logs and Models

Abstract

Conformance checking techniques can reveal commonalities and discrepancies between the observed behavior and the modeled behavior, by relating and comparing events in the event log to activities in the process model. Existing techniques quantify conformance based on mainstream models like Petri nets, which are process-centric and assume a case notion. However, the information systems which are widely used in current organizations are object-centric and do not have a case notion. As a result, existing techniques fail to accurately quantify the conformance for object-centric data. Therefore, in this paper, we propose a new approach to quantify the conformance between object-centric models and object-centric logs, and redefine metrics such as fitness and precision. At last, our approach is verified to be effective.

Keywords

• Process mining
• conformance quantifying
• metrics
• object-centric event logs
• enterprise resource planning systems