Methods and Apparatus for Improving Factor Risk Model Responsiveness

Abstract

Construction of factor risk models that better predict the future volatility of returns of a portfolio of securities such as stocks, bonds, or the like is addressed. More specifically, improved factor-factor covariance estimation is made even when the covariances change rapidly over time. Methods and techniques for achieving better accuracy, responsiveness, and stability of factor risk models are addressed.

What is claimed is: 
     
         1 . A computer-implemented method for interactively comparing different portfolio risk estimates computed using a factor risk model within a display interface, the method comprising:
 electronically receiving by a programmed computer a set of historical times selected utilizing an input device interacting with the display interface;   electronically receiving by the programmed computer an investment portfolio to be analyzed at each historical time selected;   electronically receiving by the programmed computer a time series history of factor returns at each historical time selected;   electronically receiving by the programmed computer a time series history of original factor risk models at each historical time selected, the original factor risk models comprising an exposure matrix, factor covariance matrix, and specific variance matrix for each historical time selected;   displaying within a window of the display interface a first graphical representation of a time series history of the portfolio risk computed using the original factor risk models;   displaying within the window of the display interface an alternative second graphical representation of a time series history of the portfolio risk, said alternative representation computed by:
 calculating a set of exponentially decaying weights with a fixed half-life corresponding to the time series history of factor returns; 
 computing a metric of volatility for each historical time; 
 calculating a set of volatility adjustment multipliers that is the ratio of most recent volatility metric to the measured volatility metric; 
 determining that at least one volatility adjustment multiplier is outside a predetermined range; 
 adjusting the at least one volatility adjustment multiplier to a value in the predetermined range; 
 computing an alternative factor variance for the time series of factor returns using the set of exponentially decaying weights, and volatility adjustment multipliers within the range and any adjusted volatility adjustment multiplier for any volatility multiplier determined to be outside the range; 
 creating a modified factor risk model by substituting the alternative factor variance at each historical time into the original factor risk model; 
 recomputing the portfolio risk at each historical time using the modified factor risk model; 
 outputting a second graphical representation of a time series history of the portfolio risk computed using the modified factor risk models on which the alternative second graphical representation is based; and 
   automatically identifying within the display interface time periods at which a risk difference in the portfolio risk in the first graphical representation and the second graphical representation is larger than a predetermined value.   
     
     
         2 . The computer-implemented method of  claim 1  wherein the second graphical representation is displayed only if the risk difference is larger than the predetermined value. 
     
     
         3 . The computer-implemented method of  claim 1  further comprising:
 displaying within the window of the display interface a third graphical representation of realized risk. 
 
     
     
         4 . The computer-implemented method of  claim 1  further comprising:
 aggregating risk predictions for many portfolios for multiple portfolio management. 
 
     
     
         5 . The computer-implemented method of  claim 1  wherein 0.8 is less than or equal to the ratio of most recent volatility to the measured volatility metric which is less than or equal to 1.25.