Prescriptive Analytics Using Synthetic Information

Abstract

In this chapter, the authors describe the use of synthetic information for doing prescriptive and predictive analytics. They discuss in detail how synthetic information is created by combining data from multiple sources and then describe its role in an ongoing disaster resilience study where they simulate the aftermath of a hypothetical nuclear detonation in Washington DC.

Multiscale Feedback Loops in SARS-CoV-2 Viral Evolution

“…Synthetic agents, populations, and networks provide a natural data structure that facilitates the forecasting, planning, and intervention modeling in complex social systems. Synthetic populations have been successfully applied in infrastructure modeling, computational epidemiology, and disaster response (Eubank et al, 2004; MULTISCALE FEEDBACK LOOPS IN SARS-COV-2 Parikh et al, 2013;Marathe et al, 2014). By incorporating strain competition in viral infection, the synthetic populations can provide us simulated time series of macrolevel sociobehavioral dynamics and microlevel viral population compositions.…”

A comparison of multiple behavior models in a simulation of the aftermath of an improvised nuclear detonation

“…In other work, we have looked at the effects of sending emergency broadcasts via cell phones to inform people of what has happened and to advise them to shelter in place [13,31]. This work showed that unless communication is restored (at least partially) in the region within 1 mile of ground zero, emergency broadcasts would not have a significant benefit.…”

“…In our earlier work [31], we have shown (for six-behavior with low worry model) that without restoring communication (at least partially), increasing the probability of sheltering does not help. Here also, health outcomes (i.e., number of people dead and injured) are similar for cells 1 and 3 as well as for cells 2 and 4 for both, four-behavior and six-behavior models.…”

“…The simulation is designed around a synthetic information framework [31]. We built a realistic representation of the population of the region, including demographics, daily activity patterns, and locations [2,11,8].…”