Industrial practice requires process mining techniques to not just produce models, dashboard, and data visualizations, but to help analysts get insightful answers to relevant questions. The emerging paradigm of object-centric process mining allows a new way to generate such insightful answers by embedding process mining results in the original domain data and context where the analysis question is being asked.
Yet, at the moment there is limited support for
- letting analysis formulate or define analysis questions in an intuitive way (e.g., using natural language or through simple visual constructs), and
- automatically analyzing and summarizing the data in a way that directly answers the question in a clear and insightful manner
The objective of this project is to develop and implement techniques and methods that can bridge the gap between human analyst’s interests and the data. Several different Master thesis topics are possible:
- Automated, continuous data enrichment for process analysis relevant features and abstractions by developing and implementing advanced object-centric process mining techniques
- Rigorous investigation and application of automated (statistical) root-cause analysis techniques for explaining deviations from desired behaviors or rules
- Developing and Implementing Agentic AI workflows to support human analysts in querying and summarizing object-centric event data
- Researching use of LLM Chatbots for translating natural language queries over event data into queries over knowledge graphs and summarizing/presenting answers
- Empirical evaluation of object-centric process mining analysis methods and approaches
- Other ideas from students are welcome
All projects are conducted and implemented using the open-source process mining library PromG and graph databases.
Contact: Dirk Fahland (d.fahland@tue.nl)