NLP in Process Mining: From Anomaly Detection to Automatic Improvement
- Speaker: prof. dr. Henrik Leopold, Kühne Logistics University
This event has already taken place.
Abstract
Process Mining has become an established field of research addressing a variety of problems using abroad range of methods. In this talk, I will show what Natural Language Processing (NLP) can bring to the table. Specifically, I will focus on the problem of anomaly detection. Anomaly detection in process mining aims to recognize outlying or unexpected behavior in event logs for purposes such as the removal of noise and identification of conformance violations. Existing techniques for this task are primarily frequency-based, arguing that behavior is anomalous because it is uncommon. However, such techniques ignore the semantics of recorded events and, therefore, do not take the meaning of potential anomalies into consideration. In this talk, I will show how to overcome this limitation, arguing that anomalies can be recognized when process behavior does not make sense. Building on this, I will show how NLP can also be leveraged for other relevant problems in Process Mining. I will close with an outlook how NLP could even help to automatically improve business processes.
Registration
In order to attend, you must register for the seminar. The seminar is hosted in a hybrid setting, meaning that online attendance is also possible. In case you indicate online attendance, the Google Meet link will be provided to you a few days before the seminar. For questions, feel free to contact beleidsinformatica@uhasselt.be.
About the speaker
Prof. dr. Henrik Leopold
dr. Henrik Leopold is a tenured Associate Professor at the Kühne Logistics University (KLU) and a Senior Researcher at the Hasso Plattner Institute (HPI) at the Digital Engineering Faculty, University of Potsdam. Before joining KLU/HPI in February 2019, he held positions as an Assistant Professor at the Vrije Universiteit Amsterdam (February 2015 – January 2019) and WU Vienna (April 2014 – January 2015) as well as a postdoctoral research fellow at the Humboldt University of Berlin (July 2013 – March 2014). In July 2013, he obtained a PhD degree (Dr. rer. pol.) in Information Systems from the Humboldt University of Berlin. For his thesis he received the TARGION Dissertation Award 2014 for the best doctoral thesis in the field of Information Management and the runner-up of the McKinsey Business Technology Award 2013. His research is mainly concerned with the interplay between information systems and business processes. Henrik is particularly interested in leveraging technology from the field of artificial intelligence (such as machine learning and natural language processing) to develop techniques for process mining, process analysis, and process automation. The results of his research have been published, among others, in IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Software Engineering, Decision Support Systems, and Information Systems.