World
Where and when: the structure in which agents act and how it evolves, from networks and higher-order interactions to geography.
- Network Science
- Higher-Order Networks
- Graph Machine Learning
Agents do not interact at random. They are linked by credit, trade, ownership and information, often in groups rather than in pairs, and they live in places exposed to different risks. This pillar treats space and time as a single object: the structure of these connections together with its evolution, as networks form, rewire and pass through regime shifts and transitions. The tools are network science, higher-order networks and graph machine learning.
Publications
- Network Topology Analysis and Machine Learning Techniques for Systemic Risk Prediction in U.S. Equity Markets Leveraging Graph Neural Networks (GNNs) and complex network theory to detect early warning signals of systemic risk in financial markets.
- Systemic Risk
- Graph Neural Networks
- Network Science
- Financial Machine Learning