Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture by the instructor covers the concept of coherent risk measures, focusing on the spectral approach to risk aversion. It delves into defining risk in a rigorous way, the diversification principle, Value at Risk (VaR), Expected Shortfall (ES), and the advantages and drawbacks of VaR. The lecture explores the subadditivity axiom, capital allocation, and the importance of convex risk surfaces. It also discusses the creation of new coherent risk measures through convex combinations and the estimation of spectral measures of risk. The presentation concludes with examples illustrating risk aversion functions and the implications of different risk measures on portfolio optimization.