Centeris/ProjMAN/HCist Keynote on Process Mining and the Limitations of the Directly-Follows Graphs (DFGs)


On October 15th 2019, Wil van der Aalst gave a keynote shared by three conferences: CENTERIS (International Conference on ENTERprise Information Systems),  ProjMAN (International Conference on Project MANagement), and HCist (International Conference on Health and Social Care Information Systems and Technologies). These federated conferences took place in Sousse, Tunesia. In his keynote, Wil introduced process mining and focused on the limitations of the Directly-Follows Graph (DFG). This topic is highly relevant from a practical perspective because commercial process mining tools tend to focus on such DFGs.


A DFG is a graph with nodes that correspond to activities and directed edges that corresponds to directly-follows relationships. Tools still resort to producing DFGs based on event data rather than using more sophisticated notations also able to capture concurrency. Moreover, to tackle complexity, DFGs are seamlessly simplified by removing nodes and edges based on frequency thresholds. Process-mining practitioners tend to use such simplified DFGs actively. Despite their simplicity, these DFGs may be misleading and users need to know how these process models are generated before interpreting them. In his keynote, Wil discussed the pitfalls of using the simple DFGs generated by commercial tools. Practitioners conducting a process-mining project need to understand the risks associated with the (incorrect) use of DFGs and frequency-based simplification.

If you want to learn more about the limitations of Directly-Follows Graphs (DFGs), read the paper "W.M.P. van der Aalst. A Practitioner's Guide to Process Mining: Limitations of the Directly-Follows Graph. In International Conference on Enterprise Information Systems (Centeris 2019), Procedia Computer Science 164, pages 321-328. Elsevier, 2019" which is available as open access.