Risk evaluation, control and machine learning
Contact person: Giulia Di Nunno
Keywords: Risk measures, control, deep learning, signatures, sustainability
Research group: Risk and Stochastics
Department of Mathematics
The identification of risk, its quantification, and control are of paramount importance in engineering- and financial-linked activities. The erratic weather behaviour has grown impact on the monetary risk evaluations and these are fundamental for investments’ sustainability and decision making.
The definition of appropriate risk measures both cross-sectors and environmentally sensitive is challenging in the strive to capture different data streams. Furthermore, the volumes treated are large and heavy computational methods are required, endangering the tradeoff between effectiveness and precision. So methodologies that are both efficiently descriptive and dimensionally effective are needed. Theoretical and computational results also have impact on ESG reporting.
We are interested in research proposals that are directed towards the theoretical and the computational aspects of monetary risk quantification and control, with and without climate risk.
The research proposals may span several methodological approaches within stochastic control, optimisation, and computational methods with different possibilities of application.
Methodological research topics:
- Stochastic control methods
- Data driven methods for price dynamics via deep learning
- Reinforcing learning and scenario generation
- Deep forward backward systems
- Signature methods
- Static and dynamic risk measures
Application domains:
- Risk assessment, banking and insurance systems, energy systems, sustainability
External partners:
- Gjensidige (Insurance Company)
Mentoring and internship will be offered by a relevant external partner
