Real-time probing of control-flow and data-flow in event logs

Traditional Process Mining offers batch analysis of business processes but does not transpose smoothly into online environments due to specific design constraints. Techniques adapted to support online analysis require peculiar adjustments that inherently restrict their focus to a single task. In this work, we extend the Concept Drift in Event Stream Framework (CDESF) tool to handle multiple attributes simultaneously. Our extension promotes CDESF to analyze both control-flow and data-flow characteristics in online event streams. Experiments used real and synthetic data for concept drift and anomaly detections. Results show that additional perspectives should be considered as they contain valuable information about processes.