Forecasting when an armed conflict is likely to break out is notoriously difficult, and history has shown conflict might suddenly appear out of a previously long lived and low-level dispute. However new developments in a ‘Conflict Model’ developed at the University of Cambridge and the IAE Spanish National Research Council (CSIC) in Barcelona are showing much more accuracy.
Assistant Professor Christopher Rauh, from the Faculty of Economics at the University of Cambridge, is part of a team that has investigated the signals that indicate a region might be about to turn ‘hot’, and result in civil commotion turning into either an all-out war, or at least a dispute that would result in fatalities.
Now, funding provided by the Foreign, Commonwealth & Development Office (FCDO) through the GSRA project "Dynamic Early Warning and Action Model" and the I-Link project of the Spanish National Research Council has made it possible to expand the methodology to the subnational level so that locations of violence within countries can be predicted. Furthermore, the funding has allowed the team to explain and showcase the forecast methodology to a broader audience and share the results with other research teams.
“A special feature of our model is our reliance on newspaper text. This allows us to capture changes in low level risk of conflict in countries which do not have a recent history of violence,” he says.
The main finance of this project comes from the FCDO and a research agreement with the Spanish central bank (Banco de España). Earlier stages of the project were financed by Barcelona School of Economicsseed grant and a Fundación BBVA research grant. Future expansions of the project have recently been awarded a Keynes Fund grant.
“Our model has been tested extensively by us and in a forecast competition organised by the Violence Early-Warning System (ViEWS) in which our approach performed extremely well,” adds Assistant Professor Rauh.
“The risk estimates provided here are ambitious in that they put an emphasis on cases where we can capture changes in low levels of risk in countries which do not have a recent history of violence,” he adds. “This focus can be brought to the forefront visually by switching to the ‘Prevention View’ on the website. With this it is our hope that these forecasts can be used by public decision makers who are interested in de-escalation and prevention in cases which have not, yet, escalated into full-blown conflict or are stabilising after suffering armed conflict.”
Access to the full conflict model is at: https://conflictforecast.org/
