Visual Drift Detection for Sequence Data Analysis of Business Processes

TL;DR

This paper presents a system for detecting and visualizing process drift in event sequence data, improving analysis of process changes over time with high accuracy and user-friendly visualizations.

Contribution

The paper introduces a novel system for fine-granular process drift detection and visualization, outperforming existing methods on synthetic data and effectively identifying drifts in real-world logs.

Findings

Achieved an average F-score of 0.96 on synthetic logs.

Outperformed all state-of-the-art methods in drift detection.

User study confirmed visualizations are easy to use and useful.

Abstract

Event sequence data is increasingly available in various application domains, such as business process management, software engineering, or medical pathways. Processes in these domains are typically represented as process diagrams or flow charts. So far, various techniques have been developed for automatically generating such diagrams from event sequence data. An open challenge is the visual analysis of drift phenomena when processes change over time. In this paper, we address this research gap. Our contribution is a system for fine-granular process drift detection and corresponding visualizations for event logs of executed business processes. We evaluated our system both on synthetic and real-world data. On synthetic logs, we achieved an average F-score of 0.96 and outperformed all the state-of-the-art methods. On real-world logs, we identified all types of process drifts in a comprehensive manner. Finally, we conducted a user study highlighting that our visualizations are easy to use and useful as perceived by process mining experts. In this way, our work contributes to research on process mining, event sequence analysis, and visualization of temporal data.