USING SUPERVISED MACHINE LEARNING METHODS TO IDENTIFY FACTORS THAT INFLUENCE THE PROBABILITY OF FUTURE TERRORIST ACTIVITIES
Download
Author
Boone, Ethan C.
Date
2022-12Advisor
Yoshida, Ruriko
Schuchard, Ross J.
Second Reader
Eskew, Sean, TRAC Monterey
Metadata
Show full item recordAbstract
The Defense Counter Terrorism Center (DCTC) at the Defense Intelligence Agency (DIA) focuses on classifying and predicting terrorist activities at a global scale. To accomplish this, DCTC analysts collect, process, and analyze open-source data from across the internet, including event information as reported by traditional and social media sources. This information is often aggregated in publicly available datasets, such as the Global Terrorism Database (GTD) and the Armed Conflict Location & Event Data Project (ACLED), that require additional analytic scrutiny for the DCTC team to fully exploit the contained information. In support of these efforts, this study utilizes the ACLED dataset and geospatial data to provide a monthly prediction of violent events to the DCTC team. Two models are used for comparison: a generalized network autoregressive (GNAR) time series model and an ensemble model. The results from these machine learning models will be integrated into an interactive dashboard that displays descriptive statistical information and the predictive model results about various terrorist organizations.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.Related items
Showing items related by title, author, creator and subject.
-
Performance Measures for Edge Organizations: A Preliminary Report
Desouza, Kevin C.; Roy, Sumit; Lin, Yuan (2008-06);Taking an information-processing view of organizations, we address the need for building a robust set of performance measures for Edge Organizations (EOs). Alberts and Hayes in Power to the Edge: Command, Control in the ... -
Information seeking environment of a military university
Reneker, Maxine; Jacobson, Ann; Spink, Amanda (Monterey, California. Naval Postgraduate School, 2001);In this study we examine the information use environment of the Naval Postgraduate School [NPS] as a unique academic institution educating approximately 1400 military officers from all branches of the services. This study ... -
Valued information at the right time (VIRT) and the Navy's cooperative engagement capability (CEC) - a win/win proposition
Acevedo, Rafael A. (Monterey California. Naval Postgraduate School, 2006-03);In this thesis I examine the theory of Valued Information at the Right Time (VIRT) and the benefits its implementation can provide to the Navy's best example of accurate information-sharing, the Cooperative Engagement ...