Detecting Anomalous Events in Object-centric Business Processes via Graph Neural Networks
This addresses inefficiencies, errors, or fraud detection in business processes, offering an incremental improvement over traditional methods by handling multi-case event data.
The study tackled the problem of detecting anomalies in business processes with graph-like structures by proposing a framework that uses graph neural networks and object-centric process mining, showing promising performance in detecting anomalies at activity type and attribute levels but struggling with temporal order anomalies.
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.