Forecasting Rebel Violence: How Diffusion Patterns of Violence Improve the Prediction of Future Conflicts

다국어 초록 (Multilingual Abstract)

Ensuring the safety of civilians and security personnel in conflict zones remain one of the most significant challenges to the United Nations and troop contributors. This study addresses this issue by predicting future locations of violent event based on empirical investigation of rebel activities. Making such predictions includes a three-step process. First, diffusion patterns of rebel activities are analysed using the contagion model of near-repeat victimization. This method enables to assess how the risk of violent events at a given location is transmitted to neighbouring locations within a limited time. Next, an autoregressive distributed lag model is specified based on diffusion patterns of violence identified in the first stage. This model is then applied to monthly, disaggregated data on African civil wars over the period 1997-2012. Finally, estimation results are used to predict the location of conflict in the following month at the level of 55×55km grids. The generated predictions pose both promises and challenges of conflict prediction, with the potential to provide security personnel with timely and policy-relevant information on future conflict.

참고문헌 (Reference)

1 이진영, "지리정보데이터를 활용한 전투와 폭력시위 결정 요인 분석: 미얀마 사례를 중심으로" 국제지역연구원 25 (25): 287-314, 2018

2 United Nations, "United Nations Peacekeeing: Fatalities"

3 Ward, Michael, "The Perils of Policy by p-Value: Predicting Civil Conflicts" 47 (47): 363-375, 2010

4 International Peace Institute, "The Accountability System for the Protection of Civilians: A Shared Responsibility"

5 Witmer, Frank, "Subnational Violent Conflict Forecasts for Sub-Saharan Africa, 2015–65, Using Climate-Sensitive Models" 54 (54): 175-192, 2017

6 Johnson, Shane, "Space–Time Patterns of Risk: A Cross National Assessment of Residential Burglary Victimization" 23 (23): 201-219, 2007

7 United Nations, "Report of the High-Level Independent Panel on Peace Operations"

8 Weidmann, Nils, "Predicting Conflict in Space and Time" 54 (54): 883-901, 2010

9 Hegre, Håvard, "Predicting Armed Conflict, 2010–2050" 57 (57): 250-270, 2013

10 Tollefsen, Andreas Forø, "PRIO-GRID: A Unified Spatial Data Structure" 49 (49): 363-374, 2012

11 Perry, Chris, "Machine Learning and Conflict Prediction: A Use Case" 2 (2): 2013

12 Ward, Michael, "Learning from the Past and Stepping into the Future: Toward a New Generation of Conflict Prediction" 15 (15): 473-490, 2013

13 Raleigh, Clionadh, "Introducing ACLED: An Armed Conflict Location and Event Dataset: Special Data Feature" 47 (47): 651-660, 2010

14 Townsley, Michael, "Infectious Burglaries. A Test of the Near Repeat Hypothesis" 43 (43): 615-633, 2003

15 Hegre, Håvard, "Forecasting Civil Conflict along the Shared Socioeconomic Pathways" 11 (11): 054002/1-054002/8, 2016

16 Knox, G., "Epidemiology of childhood Leukemia in Northumberland and Durham" 18 : 17-24, 1964

17 Choi, Hyun Jin, "Dominant Forms of Conflict in Changing Political Systems" 59 (59): 158-171, 2015

18 Colaresi, Michael, "Do the Robot: Lessons from Machine Learning to Improve Conflict Forecasting" 54 (54): 193-214, 2017

19 Schutte, Sebastian, "Diffusion Patterns of Violence in Civil Wars" 30 (30): 143-152, 2011

20 Raleigh, Clionadh, "Conflict Dynamics and Feedback: Explaining Change in Violence against Civilians within Conflicts" 43 (43): 848-878, 2017

21 Lalkhen, Abdul Ghaaliq, "Clinical Tests: Sensitivity and Specificity" 8 (8): 221-223, 2008

22 Youstin, Tasha, "Assessing the Generalizability of the Near Repeat Phenomenon" 38 (38): 1042-1063, 2011

23 Gleditsch, Nils Petter, "Armed Conflict 1946-2001: A New Dataset" 39 (39): 615-637, 2002

24 Wang, Zengli, "Analysis of Burglary Hot Spots and Near-Repeat Victimization in a Large Chinese City" 6 (6): 148-, 2017