SEAS Department Website

• Home

• Department Overview
• People
• Research
• Seminars & Groups
  • Financial Engineering Practitioners Seminars
  • IEOR-DRO Seminars
  • The New York Quantitative Finance Seminar
  • The Discrete Math Seminar
  • Financial Engineering Summer Informal Seminar
  • IEOR Seminars
• Admissions
• Undergraduate
• Graduate
• Industry Outreach
• Careers
• News & Events
• Resources

Seminars & Groups

Robustness and sensitivity analysis of risk measurement procedures

Date: 03-19-2007
Start Time: 6:00pm
End Time: 7:30pm
Speaker: Rama Cont, Columbia University (IEOR)
Location: 412 Schapiro CEPSR, Davis Auditorium

ABSTRACT

Measuring the risk of a financial portfolio involves two steps: estimating the loss distribution of the portfolio from available observations and computing a risk measure which summarizes the risk of the portfolio. The theoretical literature on risk measures has focused on the second step, defining a risk measure as a map associating a number to a known distribution, while the estimation problem has been studied separately from the choice of the risk measure. We study the interplay between these two steps, we formulate the notion of risk measurement procedure, which leads from a data set to a risk measure. We study properties of common risk measurement procedures used in financial risk management, in particular its coherence and sensitivity to a small change in the data set. Our study shows the lack of robustness of many commonly methods, reveals a conflict between subadditivity and robustness of risk measurement procedures and shows that including the estimation method in the analysis of risk measurement procedures is crucial.

Joint work with: Romain Degust (Columbia) and Giacomo Scandolo (Florence).

BIO

Rama Cont joined Columbia University’s IEOR Department in 2006, after spending 8 years at Ecole Polytechnique (France) as CNRS research scientist and Associate professor in Applied Mathematics. His research focuses on pricing and hedging of derivative securities,  computational methods in finance, inverse problems and model uncertainty, random graph models of social networks. Rama has taught courses at various academic institutions including: Ecole Polytechnique, Université de Paris VI, Sorbonne, Princeton, Osaka University, Université Paris-Dauphine and HEC. He has also worked as a consultant for several financial institutions on topics ranging from the optimal design of maritime transport contracts to numerical methods for pricing exotic options. He is the coauthor of "Financial Modelling with Jump Processes" (CRC Press 2003) and "Credit Derivatives and Structured Credit" (Wiley 2005).