Authors:
Anahita Ghahfarokhi
1
;
Fatemeh Akoochekian
1
;
Fareed Zandkarimi
2
and
Wil van der Aalst
1
Affiliations:
1
Process and Data Science, RWTH Aachen University, Aachen, Germany
;
2
Chair of Enterprise Systems, University of Mannheim, Mannheim, Germany
Keyword(s):
Clustering, Object-Centric Process Mining, Convergence.
Abstract:
Process mining provides various algorithms to analyze process executions based on event data. Process discovery, the most prominent category of process mining techniques, aims to discover process models from event logs. However, it leads to spaghetti models when working with real-life data. To reduce the complexity of process models, several clustering techniques have been proposed on top of event logs with a single case notion. However, in real-life processes often multiple objects are involved in a process. Recently, Object-Centric Event Logs (OCELs) have been introduced to capture the information of such processes, and several process discovery techniques have been developed on top of OCELs. Yet, the output of the discovery techniques leads to complex models. In this paper, we propose a clustering-based approach to cluster similar objects in OCELs to simplify the obtained process models. Using a case study of a real Business-to-Business (B2B) process, we demonstrate that our appro
ach reduces the complexity of the models and generates coherent subsets of objects which help the end-users gain insights into the process.
(More)