Title: Dynamic Global Conflict Risk Index
Authors: HALKIA STAMATIAFERRI STEFANOPAPAZOGLOU MICHAILVAN DAMME MARIE-SOPHIEJENKINSON GABRIELBAUMANN KATHRINTHOMAKOS DIMITRIOS
Publisher: Publications Office of the European Union
Publication Year: 2019
JRC N°: JRC118701
ISBN: 978-92-76-14133-4 (online)
ISSN: 1831-9424 (online)
Other Identifiers: EUR 30011 EN
OP KJ-NA-30011-EN-N (online)
URI: https://publications.jrc.ec.europa.eu/repository/handle/JRC118701
DOI: 10.2760/846412
Type: EUR - Scientific and Technical Research Reports
Abstract: This report presents a dynamic model of the Global Conflict Risk Index (GCRI), a conflict risk model supporting the design of European Union’s (EU) conflict prevention strategies developed by the Joint Research Centre (JRC) of the European Commission (EC) in collaboration with an expert panel of researchers and policy-makers. While most studies as well as the regression GCRI measure conflict intensity by counting the number of causalities, the proposed dynamic GCRI integrates and identifies every stage of the conflict development or de-escalation in its entire complexity. The emergence of conflict related event data sets offers researchers new ways to quantify and predict conflicts through big data. Using country-level actor-based event data sets that signal potential triggers to violent conflict such as demonstrations, strikes, or elections-related violence, the model aims at estimating the occurrence of material conflict events, under the assumption that an increase in material conflict events goes along with a decrease in material and verbal cooperation. Three potential datasets are tested in this report following a political event coding classification: (i) the Global Data on Events Location and Tone (GDELT) project, (ii) the Integrated Crisis Early Warning System (ICEWS) Dataverse dataset and (iii) the Phoenix - Open Event Data Alliance (OEDA)-Phoenix Dataset. The Artificial Intelligence (AI) methodology adopted to model the dynamic GCRI is built upon a Long-Short Term Memory (LSTM) Cell Recurrent Neural Network (RNN). These models are well-suited to classify, process and make predictions based on time series data and forecast near future events. Besides this AI model, we have set up an early warning alarm system to signal abnormal social unrest upheavals. The dynamic GCRI, through the AI and early warning alarm, seems to be able to predict the materialization of a conflict on a monthly basis. This new tool gives policy makers the possibility to observe the situation in a country on a monthly base, taking into consideration both the current and the predicted available information, and to implement preventive actions more rapidly to mitigate conflict exacerbations at an earlier stage of the conflict development cycle.
JRC Directorate:Space, Security and Migration

Files in This Item:
File Description SizeFormat 
dynamic_gcri_technical_report_1.pdf2.68 MBAdobe PDFView/Open


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.