Experiments in Conditioning Risk Estimates with Quantified News
- Friday, April 18 from 3:00 to 4:30 in Room 552; Refreshments 2:30 in Room 502
Since 1997, Northfield has used various forms of “contemporaneously observable” information to improve estimates of the future risk of securities and investment portfolios. Our first effort was to include changes in “option implied” stock volatility in our short horizon risk models. In 2007, we began to expand this concept use of information sets outside the regular data inputs to our models to adjust risk forecasts to current market conditions. Our “near horizon” family of models was commercially introduced in 2009 that used observable broad market information (e.g. VIX level) inform our models how things now are different from the way they usually are. Recently we conducted a joint research project with a group of MIT graduate students to explore how quantified news text can used to further improve risk estimates of over short time horizon, as first suggested in diBartolomeo, Mitra and Mitra (Quantitative Finance, 2009). This presentation will review the research done to date on “conditional” risk modeling, describe the various forms of quantified news feeds that are now available to investment professionals, and provide empirical data from the MIT study on the extent to which quantified has been demonstrated to be a useful ingredient to stock level risk assessment.
Dan diBartolomeo, President Northfield Information Services, Boston, MA
Mr. diBartolomeo is President and founder of Northfield Information Services, Inc. Based in Boston since 1986, Northfield develops quantitative models of financial markets. Additional Northfield staff members are located in London, Moscow, Toronto, Tokyo and Chicago. The firm’s clients include more than two hundred financial institutions in a dozen countries.
He serves on the Board of Directors of the Chicago Quantitative Alliance and is an active member of the Financial Management Association, and “QWAFAFEW”. Mr. diBartolomeo is a director of the American Computer Foundation, a former member of the Board of Directors of The Boston Computer Society, and formerly served on the industry liaison committee of the Department of Statistics and Actuarial Sciences at New Jersey Institute of Technology. Dan is a Trustee of Woodbury College, Montpelier, VT and continues his several years of service as a judge in the Moscowitz Prize competition, given for excellence in academic research on socially responsible investing. Dan has been admitted as an expert witness in federal court for litigation matters regarding investment management practices and derivatives.
Mr. diBartolomeo has written extensively for the CFA Research Foundation. This work includes “The Risk of Equity Securities and Portfolios” published in Equity Specialization Program Readings 1997 and a new wealth management monograph “Investment Management for Private, Taxable Wealth” (with Jarrod Wilcox and Jeffrey Horvitz).
Other writings include chapters in four other textbooks (The Handbook of Municipal Bonds, Advances in Portfolio Construction and Implementation, Portfolio Analysis and Linear Factor Models in Finance). His journal publications include "Socially Screened Portfolios: An Attribution of Relative Performance" (with Lloyd Kurtz) that appeared in the Fall 1996 Journal of Investing; “Investment Performance Measurement and the Probability Distribution of Pension, Assets, Liabilities and Surplus” that appeared in the Spring 1997 Journal of Performance Measurement; and two papers in Financial Analysts Journal, “Approximating the Confidence Interval on Sharpe Style Weights” (with Angelo Lobosco, July 1997) and “Mutual Fund Misclassification” (with Erik Witkowski, September 1997). His most recent publications are “Just Because We Can Doesn’t Mean We Should: Use of Daily Data in Performance Attribution” published in the Spring, 2003 Journal of Performance Measurement, and the “DSI Catholic Values 400” (with Lloyd Kurtz in Journal of Investing 2005