TY - UNPB
T1 - Challenges of Anomaly Detection in the Object-Centric Setting
T2 - Dimensions and the Role of Domain Knowledge
AU - Berti, Alessandro
AU - Jessen, Urszula
AU - van der Aalst, Wil M.P.
AU - Fahland, Dirk
PY - 2024/7/12
Y1 - 2024/7/12
N2 - Object-centric event logs, allowing events related to different objects of different object types, represent naturally the execution of business processes, such as ERP (O2C and P2P) and CRM. However, modeling such complex information requires novel process mining techniques and might result in complex sets of constraints. Object-centric anomaly detection exploits both the lifecycle and the interactions between the different objects. Therefore, anomalous patterns are proposed to the user without requiring the definition of object-centric process models. This paper proposes different methodologies for object-centric anomaly detection and discusses the role of domain knowledge for these methodologies. We discuss the advantages and limitations of Large Language Models (LLMs) in the provision of such domain knowledge. Following our experience in a real-life P2P process, we also discuss the role of algorithms (dimensionality reduction+anomaly detection), suggest some pre-processing steps, and discuss the role of feature propagation.
AB - Object-centric event logs, allowing events related to different objects of different object types, represent naturally the execution of business processes, such as ERP (O2C and P2P) and CRM. However, modeling such complex information requires novel process mining techniques and might result in complex sets of constraints. Object-centric anomaly detection exploits both the lifecycle and the interactions between the different objects. Therefore, anomalous patterns are proposed to the user without requiring the definition of object-centric process models. This paper proposes different methodologies for object-centric anomaly detection and discusses the role of domain knowledge for these methodologies. We discuss the advantages and limitations of Large Language Models (LLMs) in the provision of such domain knowledge. Following our experience in a real-life P2P process, we also discuss the role of algorithms (dimensionality reduction+anomaly detection), suggest some pre-processing steps, and discuss the role of feature propagation.
U2 - 10.48550/arXiv.2407.09023
DO - 10.48550/arXiv.2407.09023
M3 - Preprint
VL - 2407.09023
BT - Challenges of Anomaly Detection in the Object-Centric Setting
PB - arXiv.org
ER -