PhD candidate: Aaron Stefan Popa
Start: Fall 2024
This research project lies at the intersection of econometrics and machine learning, where Aaron develops estimation and forecasting methods for high-dimensional financial and economic data. He focuses on hierarchical factor models with global and local structures, nonlinear dynamics, and representation learning. To improve forecasting performance, Aaron draws on ideas from transfer learning and multi-task learning to share information across related assets, markets, and countries. His empirical work centres on financial functional data, including yield curves, implied volatility surfaces, and dependence structures such as copulas.
