Fifth PKU-NUS Annual International Conference on Quantitative Finance and Economics

Prof. Paul Glasserman

Jack R. Anderson Professor of Business, Columbia Business School

Professor Glasserman's research and teaching address risk management, derivative securities, Monte Carlo simulation, statistics and operations. Prior to joining Columbia, Glasserman was with Bell Laboratories; he has also held visiting positions at Princeton University, NYU, and the Federal Reserve Bank of New York. In 2011-2012, he was on leave from Columbia and working at the Office of Financial Research in the U.S. Treasury Department, where he continues to serve as a part-time consultant.

Glasserman's publications include the book Monte Carlo Methods in Financial Engineering (Springer, 2004), which received the 2006 Lanchester Prize and the 2005 I-Sim Outstanding Publication Award. Glasserman is a past recipient of the National Young Investigator Award from the National Science Foundation (1994 - 99), IBM University Partnership Awards (1998 - 2001), the TIMS Outstanding Simulation Publication Award (1992), the Erlang Prize (1996), the IMS Medallion from the Institute of Mathematical Statistics (2006), and a fellowship from the FDIC Center for Financial Research (2004). He received the 2004 Wilmott Award for Cutting-Edge Research in Quantitative Finance and Risk Magazine's 2007 Quant of the Year Award, and he received a U.S. patent for an option pricing method. He was named an INFORMS Fellow in 2008. He is also a recipient of the Dean's Award for Teaching Excellence (1994, 2000) and the Saul Gass Expository Writing Award (2016). Glasserman serves on the editorial boards of Operations Research, Mathematical Finance, the Journal of Derivatives, and Stochastic Systems.

Glasserman was senior vice dean of Columbia Business School in 2004-2008 and served as interim director of the Sanford C. Bernstein & Co. Center for Leadership and Ethics in 2005-2007. He currently serves as research director of the Program for Financial Studies.

Keynote title: Linear Classifiers Under Infinite Imbalance with Applications to Credit Risk

Abstract: In two-group discriminant analysis such as classifying credit risk, data from the two groups is often highly imbalanced; we may have far fewer observations from the default class than the non-default class. We study a general family of linear discriminant functions in the infinitely imbalanced limit in which the number of observations from one class grows without bound as the sample size of the other class remains fixed. We give conditions under which the intercept term diverges to negative infinity but the rest of the coefficient vector converges to a finite limit, generalizing a result of Owen (2007) for logistic regression. The form of the limit depends on the left-tail behavior of the weight function used to define the classifier. We interpret the limit from a robustness perspective as optimizing against certain worst-case alternatives. Different weight functions reflect different concerns for specificity and sensitivity in classification. We illustrate these ideas through an application to credit risk. This is joint work with Mike Li.