Challenges of Anomaly Detection in the Object-Centric Setting: Dimensions and the Role of Domain Knowledge

TL;DR

This paper explores the challenges and methodologies of anomaly detection in object-centric event logs, emphasizing the importance of domain knowledge and analyzing the potential of Large Language Models in this context.

Contribution

It introduces new approaches for object-centric anomaly detection and discusses the impact of domain knowledge and LLMs, supported by real-life process case studies.

Findings

Object-centric anomaly detection can identify complex process irregularities.

Domain knowledge enhances detection accuracy and interpretability.

LLMs have potential but also limitations in providing domain insights.

Abstract

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.