Talk: Natural Language-based Detection of Semantic Anomalies in Business Processes

Title 

Natural Language-based Detection of Semantic Anomalies in Business Processes

Abstract

Process mining is concerned with the analysis of organizational processes based on event data recorded during their execution. Process mining techniques generally analyze such data in an abstract manner, treating event data as uninformative sequences, e.g., <a, b, c, d>. However, process analysis can often benefit from going beyond this abstract view by taking the meaning of events, captured in their natural language content, into account. For instance, by looking at the textual labels of events in the context of anomaly detection, this enables one to differentiate between behavior that is uncommon, but still makes sense from infrequent behavior that hints at truly problematic situations. In this talk, Han van der Aa will provide insights into this new direction of process mining by highlighting the benefits of such a semantics-aware view for process mining and by presenting state-of-the-art approaches in this context.

Bio

Han van der Aa is a junior professor in the Data and Web Science Group at the University of Mannheim. Before that, he was an Alexander von Humboldt Fellow, working as a postdoctoral researcher in the Department of Computer Science at the Humboldt-Universität zu Berlin. He obtained a PhD from the Vrije Universiteit Amsterdam in 2018. His research interests include business process modeling, process mining, and natural language processing. His work has been published in venues such as the international conferences on Business Process Management (BPM), Advanced Information System Engineering (CAiSE), Management of Data (SIGMOD), and Data Engineering (IEEE ICDE), as well as in journals such as  IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Software Engineering, Decision Support Systems, and Information Systems.

Han van der Aa is visiting the SDPS section at DIKU from August 24-25. Contact Dmitriy Traytel at traytel@di.ku.dk, if you would like to set up an individual meeting with Han.