|Saturday, February 17|
|CS18 Survival Analysis v. 'Survival' Analysis||
Sat, Feb 17, 9:15 AM - 10:45 AM
Statistical Methods for National Security Risk Quantification and Optimal Resource Allocation (303507)
*Robert Brigantic, Pacific Northwest National Laboratory
Keywords: security, risk, optimization, consequence, vulnerability, threat
This presentation will overview statistical methods for national security risk quantification with a focus on optimal resource allocation. The techniques are applicable to a variety of venues such as mass transit or largescale public events. A key aspect of our methodology is the ability to uniquely allow the core components of risk – consequence, vulnerability, and threat to be quantified as a continuous function of time throughout the day, week, month, or year. Core statistical methods (e.g., time series forecasting) are required to forecast data that drives these various components of risk. The next step in our methodology is to assess the effectiveness, which may include a deterrence factor, of the different security resources used to counter the threat to the venue of interest. This also requires the use of statistical methods for subject matter elicitation. Lastly, we formulate the risk problem as a mathematical program which can be solved to determine the optimal allocation of constrained security resources to minimize risk as a function of time. As part of our presentations, we will demonstrate the use of open source optimization software tools to minimize the venue risk.