IDEAS home Printed from https://ideas.repec.org/a/taf/ginixx/v48y2022i4p633-648.html
   My bibliography  Save this article

A shape-based approach to conflict forecasting

Author

Listed:
  • Thomas Chadefaux

Abstract

Do conflict processes exhibit repeating patterns over time? And if so, can we exploit the recurring shapes and structures of the time series to forecast the evolution of conflict? Theory has long focused on the sequence of events that precedes conflicts (e.g., escalation or brinkmanship). Yet, current empirical research is unable to represent these complex interactions unfolding over time because it attempts to match cases on the raw value of covariates, and not on their structure or shape. As a result, it cannot easily represent real-world relations which may, for example, follow a long alternation of escalation and détente, in various orders and at various speeds. Here, I aim to address these issues using recent machine-learning methods derived from pattern recognition in time series to study the dynamics of casualties in civil war processes. I find that the methods perform well on out-of-sample forecasts of the count of the number of fatalities per month from state-based conflict. In particular, our results yield Mean Squared Errors that are lower than the competition benchmark. We discuss the implication for conflict research and the importance of comparing entire sequences rather than isolated observations in time.¿Los procesos de conflicto muestran patrones que se repiten con el paso del tiempo? Y si es así, ¿podemos aprovechar las formas y estructuras recurrentes de las series temporales para prever la evolución del conflicto? Durante mucho tiempo, la teoría se ha centrado en la secuencia de acontecimientos que preceden a los conflictos (por ejemplo, la escalada o la política suicida). Sin embargo, la investigación empírica actual es incapaz de representar estas complejas interacciones que surgen a lo largo del tiempo porque trata de comparar los casos en función del valor bruto de las covariables, y no de su estructura o forma. Por consiguiente, no puede representar fácilmente las relaciones del mundo real que, por ejemplo, pueden seguir una larga alternancia de escalada y distensión, en varios órdenes y a distintas velocidades. En este artículo, mi objetivo es abordar estas cuestiones utilizando métodos recientes de aprendizaje automático derivados del reconocimiento de patrones en series temporales para estudiar la dinámica de las bajas en los procesos de guerra civil. Me parece que los métodos funcionan bien en las previsiones fuera de muestra y, en particular, arrojan Errores Cuadráticos Medios inferiores a la referencia de la competencia. Se analizan las implicaciones para la investigación de conflictos y la importancia de comparar secuencias completas en lugar de observaciones aisladas en el tiempo.Les processus de conflit présentent-ils des schémas qui se répètent au fil du temps ? Et si tel est le cas, pouvons-nous exploiter ces formes et structures récurrentes de la chronologie pour prédire l’évolution du conflit ? La théorie s’est longtemps concentrée sur la séquence d’événements qui précède les conflits (p. ex. escalade ou stratégie du bord de l’abîme). Pourtant, les recherches empiriques actuelles ne sont pas en mesure de représenter ces interactions complexes qui se déroulent au fil du temps car elles tentent d’apparier des cas sur la base de la valeur brute de leurs covariables, et non sur celle de leur structure ou de leur forme. Elles ne parviennent par conséquent pas à représenter facilement les relations du monde réel qui peuvent, par exemple, suivre une longue alternance entre escalade et détente, dans divers ordres et à diverses vitesses. Mon objectif est ici d’aborder ces problèmes en utilisant de récentes méthodes de machine learning dérivées de la reconnaissance des schémas des chronologies pour étudier les dynamiques des pertes lors des processus de guerre civile. Je constate que ces méthodes sont performantes pour les prévisions hors échantillon, et en particulier qu’elles produisent des erreurs quadratiques moyennes inférieures par comparaison à leurs méthodes concurrentes. Nous abordons l’implication pour les recherches sur les conflits et l’importance de comparer l’intégralité des séquences plutôt que des observations isolées dans le temps.

Suggested Citation

  • Thomas Chadefaux, 2022. "A shape-based approach to conflict forecasting," International Interactions, Taylor & Francis Journals, vol. 48(4), pages 633-648, July.
  • Handle: RePEc:taf:ginixx:v:48:y:2022:i:4:p:633-648
    DOI: 10.1080/03050629.2022.2009821
    as

    Download full text from publisher

    File URL: http://hdl.handle.net/10.1080/03050629.2022.2009821
    Download Restriction: Access to full text is restricted to subscribers.

    File URL: https://libkey.io/10.1080/03050629.2022.2009821?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Racek, Daniel & Thurner, Paul & Kauermann, Goeran, 2024. "Integrating Spatio-temporal Diffusion into Statistical Forecasting Models of Armed Conflict via Non-parametric Smoothing," OSF Preprints q59dr, Center for Open Science.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:taf:ginixx:v:48:y:2022:i:4:p:633-648. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Chris Longhurst (email available below). General contact details of provider: http://www.tandfonline.com/GINI20 .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.