State-Aware Object-Centric Process Mining: Enhancing OCEL 2.0 with Explicit State Transitions

Abstract

Modern organizations manage complex processes involving multiple object types, event types, and dynamic attributes, such as stock levels, patient vital signs, or machine status, which define critical object states (e.g., Understock, Patient at Risk, Machine Down). While object-centric process mining (OCPM) with OCEL 2.0 captures these attributes, it does not systematically model state transitions, limiting insights into process dynamics. We propose State-Aware Object-Centric Process Mining (SA-OCPM), an extension of OCEL 2.0 that introduces (1) object state transition events to log changes (e.g., Normal to Understock, Patient at Risk to Stable, Machine Down to Running) and (2) object state-aware events to refine events with state context (e.g., Goods Receipt (Understock), Patient Admission (Patient at Risk), Maintenance Start (Machine Down)). Implemented in a commercial platform, SA-OCPM enables precise analysis of when, why, and how processes deviate from the optimum, as demonstrated in a logistics case study revealing inefficiencies like prolonged understock. SA-OCPM's state-based approach enhances diagnostic granularity and is applicable to domains like healthcare, manufacturing, and customer relationship management.

Authors 3

1. Alessandro Berti Aachen Process and Data Science (PADS)

   RWTH Aachen University

   Affiliation as printed

   Process and Data Science (PADS), RWTH Aachen University

2. Dina Kretzschmann Aachen Process and Data Science (PADS)

   RWTH Aachen University

   Affiliation as printed

   Process and Data Science (PADS), RWTH Aachen University

3. Wil M. P. van der Aalst Aachen Process and Data Science (PADS)

   RWTH Aachen University

   Affiliation as printed

   Celonis

   Process and Data Science (PADS), RWTH Aachen University