The 2023/24 VIEWS Prediction challenge: Predicting the number of fatalities in armed conflict, with uncertainty

Abstract Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fail to represent the inherent uncertainty in the distribution of conflict fatalities. Yet, current early warning systems are preponderantly focused on providing point estimates, while efforts to forecast conflict fatalities as a probability distribution remain sparse. Building on the predecessor VIEWS competition, we organize a prediction challenge to encourage endeavours in this direction. We invite researchers across multiple disciplinary fields, from conflict studies to computer science, to forecast the number of fatalities in state-based armed conflicts, in the form of the UCDP ‘best’ estimates aggregated to two units of analysis (country-months and PRIO-GRID-months), with estimates of uncertainty. This article introduces the goal and motivation behind the prediction challenge, presents a set of evaluation metrics to assess the performance of the forecasting models, describes the benchmark models which the contributions are evaluated against, and summarizes the salient features of the submitted contributions.

Authors

Institutions

Publication Details

Journal
Journal of Peace Research
Published
2025-05-06
DOI
https://doi.org/10.1177/00223433241300862
Citations
4
Primary Topic
Insurance, Mortality, Demography, Risk Management
Type
article
Field-Weighted Citation Impact
22.37

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The 2023/24 VIEWS Prediction challenge: Predicting the number of fatalities in armed conflict, with uncertainty

Christoph Dworschak, Angelica Lindqvist-McGowan, Hannes Mueller, Sonja Häffner et al.
4 citations
Journal of Peace Research
Insurance, Mortality, Demography, Risk Management
22.37
article

The 2023/24 VIEWS Prediction challenge: Predicting the number of fatalities in armed conflict, with uncertainty

Christoph Dworschak, Angelica Lindqvist-McGowan, Hannes Mueller, Sonja Häffner, Lotta Rüter, Marco Nicola Binetti, Luca Macis, Nils W. Metternich, Kristian Skrede Gleditsch, Martin Hofer, David Randahl, Marius Mehrl, David Muchlinski, Johan R. Vegelius, Patrick T. Brandt, Vito D’Orazio, Michael P. Colaresi, Thomas Chadefaux, Elena Siletti, Cornelius Fritz, Hartmut Frank, Håvard Hegre, Jonas Vestby, Christian Oswald, Paola Vesco, Julian Walterskirchen, Christopher Rauh, Marco Tagliapietra, Paola Pisano, F Becker, Tobias Bohne, Simon Drauz, Finn L. Klebe, Alexandra Malaga, Daniel Mittermaier, Thomas Schincariol, Benjamin Seimon, Chandler Thornhill, Alexa Timlick, Noorain Syed Kazmi, Tobias Bodentien
article en
4 citations

Abstract

Abstract Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fail to represent the inherent uncertainty in the distribution of conflict fatalities. Yet, current early warning systems are preponderantly focused on providing point estimates, while efforts to forecast conflict fatalities as a probability distribution remain sparse. Building on the predecessor VIEWS competition, we organize a prediction challenge to encourage endeavours in this direction. We invite researchers across multiple disciplinary fields, from conflict studies to computer science, to forecast the number of fatalities in state-based armed conflicts, in the form of the UCDP ‘best’ estimates aggregated to two units of analysis (country-months and PRIO-GRID-months), with estimates of uncertainty. This article introduces the goal and motivation behind the prediction challenge, presents a set of evaluation metrics to assess the performance of the forecasting models, describes the benchmark models which the contributions are evaluated against, and summarizes the salient features of the submitted contributions.

Journal of Peace ResearchVol. 62(6)
Karlsruhe Institute of Technology (DE), University of Essex (GB), West Virginia University (US), Uppsala University (SE), Georgia Institute of Technology (US), University of Leeds (GB), The University of Texas at Dallas (US), Trinity College Dublin (IE), Universität der Bundeswehr München (DE), Fundación de Estudios de Economía Aplicada (ES), Institut d'Anàlisi Econòmica (ES), Centre for Economic Policy Research (GB), Early Warning (United States) (US), Barcelona School of Economics (ES), University College London (GB), University of York (GB), University of Turin (IT), Peace Research Institute Oslo (NO)
Norges Forskningsråd, H2020 European Research Council
Openalex Percentile: Top 1%
Insurance, Mortality, Demography, Risk Management
22.37
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.