10.7910/DVN/UX8GUZRauh, ChristopherChristopherRauh0000-0001-6353-1640University of CambridgeHarvard Dataverse2022Social SciencesRauh, ChristopherChristopherRauhUniversity of Cambridge2022-03-212022-03-2224572576739669233273198512586691851701940370154154789413336190203087935847819071251375110681934475052483995140628296232639582403234149974250843182318812545965128651282071655113965355481434429350802624122940687556875511252983179311711277081015719993113685143905439706296552241457939390543970629655224144543246443328482694250781518933615528824524825359637674295995096852078373942871957939609366093660523601496014961573450654573722765272612517970057882867041492138913442622701527936223852310529703872931764117361239161265625356931407303047065962291401application/x-stata-syntaxapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/tab-separated-valuestext/tab-separated-valuesapplication/x-stata-14text/tab-separated-valuesapplication/x-stata-syntaxtext/x-python-scriptapplication/x-stata-syntaxapplication/x-ipynb+jsonapplication/pdftext/tab-separated-valuestext/x-python-scripttext/tab-separated-valuesapplication/x-stata-syntaxapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/tab-separated-valuesapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/x-python-scriptapplication/x-ipynb+jsontext/tab-separated-valuesapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/tab-separated-valuestext/tab-separated-valuestext/tab-separated-valuestext/tab-separated-valuestext/tab-separated-valuesapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/x-stata-syntaxapplication/x-stata-syntaxtext/rtfapplication/pdfapplication/x-ipynb+jsonapplication/pdfapplication/pdfapplication/x-stata-syntaxapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/tab-separated-valuesapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdftext/csv1.0CC0 WaiverIn this article we propose a framework to tackle conflict prevention, an issue which has received interest in several policy areas. A key challenge of conflict forecasting for prevention is that outbreaks of conflict in previously peaceful countries are rare events and therefore hard to predict. To make progress in this hard problem, this project summarizes more than four million newspaper articles using a topic model. The topics are then fed into a random forest to predict conflict risk, which is then integrated into a simple static framework in which a decision maker decides on the optimal number of interventions to minimize the total cost of conflict and intervention. According to the stylized model, cost savings compared to not intervening pre-conflict are over US$1 trillion even with relatively ineffective interventions, and US$13 trillion with effective interventions.