Der Lehrstuhl auf der 20. International Conference on Business Process Management (BPM 2022)
Nach langer Pause war der Lehrstuhl für Digital Industrial Service Systems in diesem Jahr wieder in Präsenz bei der International Conference on Business Process Management (BPM 2022) vertreten. Die Konferenz fand vom 11. bis zum 16. September 2022 in Münster statt und ist eine der wichtigsten Konferenzen für Geschäftsprozessmanagement. Im Folgenden einige Eindrücke von der Konferenz und ein Ausschnitt unseres Workshop-Beitrags. Den vollständigen Artikel erhalten Sie über den Bild-Link.
Text-aware predictive process monitoring with contextualized word embeddings
Lena Cabrera, Sven Weinzierl, Sandra Zilker, Martin Matzner
Predictive process monitoring (PPM) is the discipline of exploiting event logs of business processes to construct predictive models for anticipating different properties of running business processes. The event logs used contain control flow information of past process executions and, often, additional information about the context in which a process ran. As the process context can add valuable information to a predictive model, recent PPM techniques often incorporate it to improve process predictions. While most techniques incorporate context information as well-structured numerical and categorical context features, only a few utilize unstructured text from process-related comment fields, emails, or documents. The few existing text-aware PPM approaches are limited in capturing semantic information, as different meanings of the same word occurring in different contexts, i.e., sentences, are ignored. This paper addresses this limitation by proposing a text-aware PPM technique using contextualized word embeddings to predict the next activity and the next timestamp of running process instances. An experimental evaluation with a text-enriched real-life event log shows that our technique can outperform text-aware PPM approaches relying on non-contextualized word embeddings in terms of predictive performance.