Unlocking Insights: Building a Proprietary PE Dataset from GP Reports
Advisor: Dr. Sara Boni, Dr. Max Knicker & Julius Maisch, MSc.
Type: Master's Thesis
Starting Options: 15/09/2025 (Note: This thesis starts with a mandatory full-day kick-off event. For this reason, alternative starting dates cannot be accommodated.)
Overview
Our chair is engaged in a long-term effort to build one of Europe’s most detailed proprietary datasets on private markets. This initiative involves transforming unstructured transaction materials into structured, analysis-ready data. The project is conducted in collaboration with a data-driven alternative asset management firm and offers students a unique opportunity to work at the intersection of academic research and real-world investment practice.
Students participate in this initiative as part of a cohort-based process that has been refined over each cohort. Working in groups, they follow a clear and proven workflow for transforming GP reports into structured data, while benefiting from a strong support network and direct interaction with both academic researchers and industry practitioners.
After completing the data phase together with their cohort, students move on to the thesis phase, where they define their individual research question in consultation with the supervisors. Drawing on the structured dataset, each thesis explores an empirical aspect of private markets, combining independent analysis with the foundation of a well-established process.
Structure & Timeline
Each cohort works through a dual-phase structure that ensures students gain hands-on experience with real-world deal-level information and deep insight into private equity.
- Data Phase: 3 months part-time (in-person* at the chair, minimum 2 days per week) involvement in structured data extraction and validation
- Thesis Phase: 3 months of full-time thesis writing on an approved topic using the structured data
Thesis Topics
Students will define their research question in consultation with the advisors. Possible directions include (but are not limited to):
- Deal structuring and value creation
- Sponsor characteristics and investment outcomes
- Distress and turnaround investing
- Cross-sectional determinants of fund performance
Requirements
- A reliable and structured working style, with attention to detail.
- Basic proficiency in Excel and willingness to learn new tools.
- Motivation to contribute consistently within a collaborative project setting.
Supervision & Support
We run a well-established supervision process that guides students smoothly from start to finish.
- Kick-Off Day:
- Guided tour of our lab facilities
- Meet-and-greet with supervisors, the chair, and representatives from our partner fund
- Private Equity crash course based on TUM’s flagship PE module
- Guest talk from the Head of Investments of our partner asset manager
- Hands-on onboarding with our custom data entry systems
- Data Phase Support:
- Multi-level support network: peer collaboration, guidance from experienced students, and direct access to PhD researchers and a postdoc
- Weekly Q&A sessions to address challenges, monitor progress, and provide feedback
- Thesis Supervision:
- Students choose one of three experts (econometrics, data science, or an industry quant).
- Additional one-on-one support available on demand, including help with identifying relevant academic sources and research methodology.
Contact & Application
If you are interested in writing your thesis on this topic, please indicate this in your application. Please note that this topic can be expanded and/or taken in other directions depending on the student's own interests and ideas.
Notes
*We would love to offer hybrid or remote options - but the real-world data you’ll be working with is highly confidential and hence cannot leave our labs.