Master’s Thesis - LLM-Based Moving-Target Detection and Signal Generation in Economic Narratives
About the Role
Location Germany Bayern Erlangen
1. Country: GERMANY
2. State/Province/County: Nordrhein-Westfalen
3. City: Muelheim an der Ruhr
4. Country: GERMANY
5. State/Province/County: Hamburg
6. City: Hamburg
Remote vs. Office Hybrid (Remote/Office) Company Siemens Energy Global GmbH & Co. KG Organization SE CFO Business Unit Gas Services Full / Part time Full-time Experience Level Student (Not Yet Graduated) Location: ERL S SK 3Mode of Employment: Full-time / Fixed TermA Snapshot of Your Day You work with public economic and policy-related text and investigate how recurring communication changes over time. exploring LLM-based methods for identifying newly emphasized, de-emphasized, or disappearing themes and exploring how such changes can be transformed into structured and interpretable signal.How You’ll Make an Impact
7. Development of a research approach for temporal comparison of recurring economic or policy communication
8. Exploration of LLM-based methods for identifying newly emphasized, de-emphasized, or disappearing themes
9. Implementation of a prototype for structured signal generation from changes in narrative emphasis
10. Evaluation of alternative methodological approaches for temporal text comparison and signal stability
11. Documentation of methodology, findings, and limitations for future reuse in applied text analytics
12. Support with the translation of research results into interpretable signal concepts for forecasting-related use cases
What You Bring
13. Studies in Data Science, Computer Science, Artificial Intelligence, or a related field at Master’s level
14. Knowledge of Python-based data processing and NLP workflows for text analysis and prototyping
15. Interest in large language models, prompt-based methods, and temporal text analysis in economic or business-related contexts
16. Understanding of research-oriented experimentation and evaluation design for comparing methodological alternatives
17. Ability to work independently on implementation, analysis, and technical documentation in an applied research environment
18. Experience with embeddings, prompt-based extraction, topic modeling, or text clustering as an advantage