Research on Quantitative Finance
Quantitative Finance is one of the department's tracks for graduate education and
research. Faculty is working on different areas of quantitative finance.
Robert Frey, Research Professor and Director for Quantitative Finance, had worked in an array of operations research related managerial positions before earning his Applied Math PhD in 1986. Then he became involved in designing mathematically based financial trading systems, first at Morgan Stanley, then at Kepler Associates, and finally at Renaissance Technologies, from which he retired at the rank of Managing Director in 2004. Frey is leading his own hedge fund, Frey Quantitative Strategies.
Stan Uryasev, Frey Family Endowed Chair and Co-Director for Quantitative Finance, is focused on efficient computer modeling and optimization techniques and their applications in finance and DOD projects. He is a co-inventor of Conditional Value-at-Risk (CVaR) optimization approach. His research on risk measures is summarized in Risk Quadrangle concept which combines risk management, portfolio optimization, utility theory, and statistical estimation. This concept led to convex and linear programming algorithms for linear regression of CVaR. Drawdown portfolio optimization and Drawdown Alpha/Beta characteristics are used in active investments. Currently Stan works on applications of a new risk measure called Buffered Probability of Exceedance(bPOE). In particular, bPOE resulted in algorithms for maximization of AUC and bAUC machine learning. Find most popular Stan’s publications at Google Scholar.
Andrew Mullhaupt’s original research interests involved partial differential equations and linear algebra. He has worked on Wall Street for over 20 years designing mathematically based trading systems, first at Morgan Stanley, then at Renaissance Technologies, and most recently at SAC Capital where he was Director of Research for the SAC’s Meridian Fund.
Haipeng Xing’s research interests spread over three disciplines: quantitative finance, statistics, and macroeconomics. In quantitative finance, he has been working on problems on surveillance and early warning models of structural breaks in the credit market, financial time series models with multiple change-points, analysis of high- and ultra-high frequency trading data, high-dimensional time series models for stocks’ returns, volatilities, and volumes. He worked on portfolio optimization and asset allocation, and applied stochastic control methods to derivative pricing and trading strategies. In statistics, his interest focuses on estimation, detection, and control of multiple change-points in low- and high-dimensional systems and their applications to econometrics, finance, and genomic data analysis. In macroeconomics, he is mainly interested in methodological development of endogenous structural transformation models and their applications in economic analysis.
Pawel Polak’s research interest is in machine learning, big data, predictive modeling, and signal processing with shrinkage and regularization. His research involves statistical modeling of large-dimensional stochastic processes with heavy-tailed distributions, sparse signal processing with breakpoints, and multivariate time series analysis models arising in a variety of settings, ranging from portfolio optimization, factor modeling, asset pricing, multivariate volatility modeling, risk prediction, and options pricing.