[Deep Tech] Early success prediction of Deep Tech Startups

📌 Key facts

🎯 Objective: Predicting the success of Deep Tech Startups using Machine Learning and Large Language Models models to estimate venture performance in early startup stages

⏱️ When: Start date is flexible! Applications are open!

📥 How to apply: Send us an e-mail (at the end of this page) with your CV and grade report

❗IMPORTANT: Python programming skills required

• 📌 Key facts
• 💡 Background
• 🎯 Goals
• 🦾 Who We Are
• 🧠 Topics of Interest
• 🎓 Profile
• 📚 Further Reading
• 📝 How to Apply

💡 Background

Deep Tech is based on high-tech innovation in significant scientific advances (e.g., Artificial Intelligence, Biotechnology, Quantum Computing, and Advanced Materials). Unlike traditional startups, Deep Tech startups require substantial time and capital to bring their technologies to market due to implementation, investment and collaborative risk (Romme, 2022).

Predicting the success of startups, particularly in the Deep Tech sector, is a challenging endeavor that has historically depended on qualitative assessments and financial metrics. Machine learning models, which have proven successful for traditional startups, offer accurate and scalable predictions. These models enable investors and entrepreneurs to make well-informed decisions, mitigate risks, and allocate resources more efficiently.(Te et al., 2023).

Large Language Models represent a significant advancement in the field of AI. LLMs can analyze unstructured data sources, such as self-descriptions, press releases, and social media posts, to extract valuable insights that were previously difficult to quantify. By integrating LLMs with traditional machine learning techniques, we can create more comprehensive and nuanced models (Maarouf et al., 2024)

🎯 Goals

Your goal is to develop and validate a machine learning model that predicts the success of Deep Tech startups:

1. Data Collection and Preparation: Utilizing data from Dealroom, LinkedIn and other relevant sources to gather comprehensive information on startups
2. Feature Engineering: Creating and optimizing features from both structured and unstructured data to enhance model performance
3. Model Development: Implementing and fine-tuning machine learning algorithms and fused large language models to predict startup success
4. Evaluation: Developing robust evaluation metrics to assess model performance

🦾 Who We Are

The Chair for Strategy and Organization is focused on research with impact. This means we do not want to repeat old ideas and base our research solely on the research people did 10 years ago. Instead, we currently research topics that will shape the future. Topics include Agile Organizations and Digital Disruption, Blockchain Technology, Creativity and Innovation, Digital Transformation and Business Model Innovation, Diversity, Education: Education Technology and Performance Management, HRTech, Leadership, and Teams. We are always early in noticing trends, technologies, strategies, and organizations that shape the future, which has its ups and downs.

🧠 Topics of Interest

• Deep Tech
• Venture capital and funding
• Entrepreneurial success factors
• Large language models
• Data collection, validation & Data quality

🎓 Profile

• Your work is super accurate. There is no room for 80/20, thus your academic track record is excellent!
• Python programming experience is required
• Reliable, self-driven working style and proactive communication
• Analytical Thinking and Statistical Knowledge
• Interest in Entrepreneurship, Deep Tech, Machine Learning and Large Language Models

📚 Further Reading

• Maarouf, A., Feuerriegel, S., & Pröllochs, N. (2024). A Fused Large Language Model for Predicting Startup Success. European Journal of Operational Research, S0377221724007136. https://doi.org/10.1016/j.ejor.2024.09.011
• Te, Y.-F., Wieland, M., Frey, M., Pyatigorskaya, A., Schiffer, P., & Grabner, H. (2023). Making it into a successful series A funding: An analysis of Crunchbase and LinkedIn data. The Journal of Finance and Data Science, 9, 100099. https://doi.org/10.1016/j.jfds.2023.100099
• Romme, A. G. L. (2022). Against All Odds: How Eindhoven Emerged as a Deeptech Ecosystem. Systems, 10(4), 119. https://doi.org/10.3390/systems10040119

📝 How to Apply

If you are interested, please contact Jannik Nolden by submitting 1) your desired starting date, 2) CV, 3) grade report and 4) a short motivation letter why you are interested in this topic and how you are a good fit for it.

Jannik Nolden (Chair for Strategy and Organization) 👉 jannik.nolden@tum.de