Several metrics are widely used to assess a firms’ risk exposure, including credit scores provided by ratings agencies such as Standard & Poor’s, Moody’s and Fitch, which measure the probability, or cost, of default. These credit scores, however, are not transparent as the rating methodology is not required to be publicly disclosed. Moreover, existing credit ratings only provide a generic score that is hard to interpret.
This project will use machine learning techniques to construct an accurate, transparent, and explainable corporate credit and risk exposure score that considers interdependencies in a firm’s network, with the objective of improving decision making for both investment and policy development, as well as to influence the standards by which credit-rating agencies measure risk.
Applications of Machine Learning in Finance, particularly Portfolio Risk Optimization and Trading.
BS Physics, University of California at Irvine.
MSc Corporate & Financial Risk Management, University of Sussex.
MBA, IE Business School.
Professionally, I spent 3 years as an investment analyst at a boutique investment company in the US working on public and private investments. After that I spent 7 years as an entrepreneur in Germany where I founded a self-storage company which was acquired in 2021.
Dr. Stylianos Asimakopoulos
Dr. Özgür Şimşek