(Generative/Graph) Machine Learning-based Automated Redesign of Business Processes

Thesis (BA/MA)

Advisor(s): Maximilian Harl (maximilian.harl@tum.de)

CONTEXT

Business process redesign (BPR) traditionally relies on manual analysis and expert-driven restructuring of processes. However, with the increasing availability of event logs and recent advances in machine learning, it is now possible to automate parts of this redesign work. Current research explores how process models can be represented and how ML techniques can predict future process structures, derive change propositions, and support redesign in runtime environments. Early results show that ML-based approaches can outperform classical baselines in predicting how processes evolve over time, opening the door to more proactive and data-driven BPR.
This thesis contributes to this emerging research area by implementing such an ML-based technique, evaluating its performance, and validating its usefulness in real-world settings. Students will gain hands-on experience in machine learning, process mining, and empirical evaluation.

 

TASK(S)

• Implement a ML-based techniques for predicting structural changes in business process models
• Benchmark ML models for graph or process prediction
• Apply the technique to real-world or public event logs and assess redesign

• Evaluate automated business process redesign techniques in real world settings

   

REQUIREMENTS

• High degree of autonomy and individual responsibility
• Interest in current IS topics with a focus on machine learning and business process management
• Strong interest in machine learning and data-driven process analysis
• Experience with Python; willingness to work with ML libraries
• Experience in & willingness to conduct scientific studies, analyze qualitative and quantitative data, and learn about scientific writing

• Structured, reliable, and self-motivated work style

   

FURTHER INFORMATION

The thesis can be written in English or German. The topic can also be adapted to your interests. If you have further questions, please do not hesitate to contact me directly. Please send your application including our application form, a current transcript of records, and your CV to maximilian.harl(at)tum.de. Please note that we can only consider applications with complete documents.