Claus Huber is a Portfolio Manager at Deka Investment LLC, Frankfurt, where he helps to develop new quantitative investment products. As the founder of Rodex Risk Advisers LLC, based in Altendorf (Switzerland), he advised clients on risk management and quantitative investment solutions, for example, a Machine Learning approach to select hedge fund managers. He has extensive experience as entrepreneur, risk manager, credit strategist, hedge fund analyst and government bond trader and worked for hedge funds, banks and insurance companies.
Machine Learning for Visual Portfolio Risk Analysis
A very valuable feature of the Self-Organising Map, a method of Machine Learning, is its visualisation capabilities. We show how the Self-Organising Map can be deployed to visualise the risk structure in a portfolio, in particular for assets for which no risk models exist. Some examples to this end are the visualisation of risk concentrations, identifying diversifiers and scenario analysis. Real-world applications are the selection of hedge fund managers or the analysis of a portfolio of Alternative Risk Premia.