A Robust and Accurate Approach to Detect Process Drifts from Event Streams
This addresses the need for robust process drift detection in business process management, but it is incremental as it builds on existing methods to handle noise.
The paper tackles the problem of detecting process drifts in event streams, which are often affected by noise, and proposes an offline method that uses candidate drift points and bidirectional search to accurately locate changes; results show it consistently reports accurate drift times with fast detection speeds.
Business processes are bound to evolve as a form of adaption to changes, and such changes are referred as process drifts. Current process drift detection methods perform well on clean event log data, but the performance can be tremendously affected by noises. A good process drift detection method should be accurate, fast, and robust to noises. In this paper, we propose an offline process drift detection method which identifies each newly observed behaviour as a candidate drift point and checks if the new behaviour can signify significant changes to the original process behaviours. In addition, a bidirectional search method is proposed to accurately locate both the adding and removing of behaviours. The proposed method can accurately detect drift points from event logs and is robust to noises. Both artificial and real-life event logs are used to evaluate our method. Results show that our method can consistently report accurate process drift time while maintaining a reasonably fast detection speed.