Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Detecting Anomalous Events in Object-centric Business Processes via Graph Neural Networks

Alessandro Niro, Michael Werner

TL;DR

This study proposes a novel framework for anomaly detection in business processes that exploits graph neural networks and the enhanced information offered by object-centric process mining, which provides promising performance in detecting anomalies at the activity type and attributes level.

Abstract

Detecting anomalies is important for identifying inefficiencies, errors, or fraud in business processes. Traditional process mining approaches focus on analyzing 'flattened', sequential, event logs based on a single case notion. However, many real-world process executions exhibit a graph-like structure, where events can be associated with multiple cases. Flattening event logs requires selecting a single case identifier which creates a gap with the real event data and artificially introduces anomalies in the event logs. Object-centric process mining avoids these limitations by allowing events to be related to different cases. This study proposes a novel framework for anomaly detection in business processes that exploits graph neural networks and the enhanced information offered by object-centric process mining. We first reconstruct and represent the process dependencies of the object-centric event logs as attributed graphs and then employ a graph convolutional autoencoder architecture to detect anomalous events. Our results show that our approach provides promising performance in detecting anomalies at the activity type and attributes level, although it struggles to detect anomalies in the temporal order of events.

Detecting Anomalous Events in Object-centric Business Processes via Graph Neural Networks

TL;DR

This study proposes a novel framework for anomaly detection in business processes that exploits graph neural networks and the enhanced information offered by object-centric process mining, which provides promising performance in detecting anomalies at the activity type and attributes level.

Abstract

Detecting anomalies is important for identifying inefficiencies, errors, or fraud in business processes. Traditional process mining approaches focus on analyzing 'flattened', sequential, event logs based on a single case notion. However, many real-world process executions exhibit a graph-like structure, where events can be associated with multiple cases. Flattening event logs requires selecting a single case identifier which creates a gap with the real event data and artificially introduces anomalies in the event logs. Object-centric process mining avoids these limitations by allowing events to be related to different cases. This study proposes a novel framework for anomaly detection in business processes that exploits graph neural networks and the enhanced information offered by object-centric process mining. We first reconstruct and represent the process dependencies of the object-centric event logs as attributed graphs and then employ a graph convolutional autoencoder architecture to detect anomalous events. Our results show that our approach provides promising performance in detecting anomalies at the activity type and attributes level, although it struggles to detect anomalies in the temporal order of events.
Paper Structure (19 sections, 4 equations, 2 figures, 4 tables)

This paper contains 19 sections, 4 equations, 2 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Preliminaries and Background
  3. Object-centric Process Mining.
  4. Problem Statement.
  5. Related Work
  6. Anomaly Detection in Business Processes.
  7. Graph Neural Networks.
  8. Method
  9. Approach Overview.
  10. Data Preprocessing
  11. Process Instances Reconstruction.
  12. Input Graph Encoding.
  13. GCNAE Architecture
  14. IQR Heuristic: Automatic Thresholding and Anomaly Labeling
  15. Experiments
  16. ...and 4 more sections

Figures (2)

  • Figure 1: An overview of our proposed approach.
  • Figure 2: The reconstructed process instances for the object-centric event log in Table \ref{['tab:ocel']}.

Theorems & Definitions (5)

  • definition thmcounterdefinition: Object-centric Event Log
  • definition thmcounterdefinition: Object-centric Process Instance
  • definition thmcounterdefinition: Event Anomaly Detection
  • definition thmcounterdefinition: Adjacency Matrix , $\mathbf{A}$
  • definition thmcounterdefinition: Feature Matrix , $\mathbf{X}$