Evaluating the Value of Information in the Presence of High Uncertainty
CONNECTICUT UNIV STORRS DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE
Pagination or Media Count:
Context-driven decision making relies upon a multitude of information, but placing a tangible value on these pieces of information is an upcoming problem in the Information Age. In an application to combating piracy, the U.S. Navy relies upon a probability surface which integrates intelligence, commercial shipping routes, and meteorological and oceanographic METOC information, and forms the basis for predicting geo-temporal patterns of pirate presence and attack, commonly referred to as Piracy Attack Risk Surface PARS. Degradation in the quality of this information lowers the quality of PARS, which forms the basis for counter-piracy surveillance and interdiction asset allocations to geographic regions. In this paper, we investigate the value of PARS in the presence of uncertainty in intelligence and weather when it is used in an asset allocation algorithm that seeks to minimize the probability of success of a pirate attack. The algorithm allocates both interdiction and surveillance assets to deter pirate activities. We perform a sensitivity analysis using hypothetical counter-piracy scenarios to quantify the value of the information.
- Sociology and Law
- Statistics and Probability
- Computer Programming and Software
- Naval Surface Warfare