TARGET - TAming unceRtainty in enerGy markETs: forecasting with dependency structures

• Applicant: Professor Dr. Florian Ziel
• Subject Area: Statistics and Econometrics ; Accounting and Finance ; Electrical Energy Systems, Power Management, Power Electronics, Electrical Machines and Drives ; Methods in Artificial Intelligence and Machine Learning ; Operations Management and Computer Science for Business Administration
• Term: since 2026
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 569562071

This research project aims to develop novel statistical and econometric time series methods for energy markets, addressing key issues in modeling uncertainty. The project is divided into two work packages focusing on short-term and long-term risks. The first one explores higher-moment risks and dependency structures beyond correlation for short-term forecasting. We plan to extend established linear models by integrating high-dimensional state-space frameworks and advanced quantile-based approaches, enhancing the modeling of extreme events. Additionally, copula-based techniques will be employed to capture complex dependency structures and tail risks. The second package focuses on long-term risks, persistence, and the integration of fundamental information. By incorporating expert-informed fundamental models alongside data-driven techniques, we aim to enhance predictive accuracy and robustness. The proposed methodologies contribute to the advancement of risk management and forecasting in energy markets, providing valuable insights for both academic research and industry applications.

• DFG Programme: Research Grants
• International Connection: Czech Republic
• Cooperation Partner: Professor Dr. Jozef Barunik