Spatial Forecast Methods for Terrorist Events in Urban Environments
Terrorist events such as suicide bombings are rare yet extremely destructive events. Responses to such events are even rarer, because they require forecasting methods for effective prevention and early detection. While many forecasting methods are available, few are designed for conflict scenarios. This paper builds on previous work in forecasting criminal behavior using spatial choice models. Specifically we describe the fusion of two techniques for modeling the spatial choice of suicide bombers into a unified forecast that combines spatial likelihood modeling of environmental characteristics with logistic regression modeling of demographic features. In addition to describing the approach we also provide motivation for the fusion of the methods and contrast the results obtained with those from the more common kernel density estimation methods that do not account for variation in the event space. We give an example of successful use of this combined method and an evaluation of its performance. We conclude that the fusion method shows improvement over other methods and greater scalability for combining larger numbers of spatial forecasting methods than were previously available.
Unable to display preview. Download preview PDF.
- 1.Cordesman, A.H.: The Lessons of Afghansitan: War fighting, Intelligence, and Force Transformation. The Center for Strategic and International Studies, Washington, D.C. (2002)Google Scholar
- 2.U.S. Department of Justice. FY 2002 Program Performance Report. Strategic Goal One: Protect America Against the Threat of Terrorism, Downloaded from http://www.usdoj.gov/ag/annualreports/ar2002/sg1finalacctperftpt.htm on October 20 (2003)
- 3.Parzen, E.: On Estimation of Probability Density Function and Mode. Annals Math. Statist, 1065–1076 (1962)Google Scholar
- 4.International Policy Institutes for Counter-Terrorism, International Terrorism/Terror Attack Database, http://www.ict.org.il/
- 6.Lattin, J., Carrol, J.D.: Analyzing Multivariate Data. ch. 13. Thomson Learning Inc. (2003)Google Scholar
- 7.Liu, H., Brown, D.E.: Criminal incident prediction using a point-pattern-based density model. International Journal of Forecasting, 603–622Google Scholar