In this research, we focused on armed conflicts and related violence. The study reviewed the use of machine learning to predict the likelihood of conflict escalation and the role of conditioning factors. The results showed that machine learning and predictive models could help identify conflict-prone locations and geospatial factors contributing to conflict escalation. The study found 46 relevant papers and emphasized the importance of considering unique predictors and conditioning factors for each conflict. It was found that the conflict susceptibility of a region is influenced principally by its socioeconomic conditions and its political/governance factors. We concluded that machine learning has the potential to be a valuable tool in conflict analysis and, therefore, it can be an asset in conflict mitigation and prevention, but the accuracy of the models depends on data quality and the careful selection of conditioning factors. Future research should aim to refine the methodology for more accurate prediction of the models.

Identifying Conditioning Factors and Predictors of Conflict Likelihood for Machine Learning Models: A Literature Review / Obukhov, T.; Brovelli, M. A.. - In: ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION. - ISSN 2220-9964. - 12:8(2023), pp. 1-22. [10.3390/ijgi12080322]

Identifying Conditioning Factors and Predictors of Conflict Likelihood for Machine Learning Models: A Literature Review

T. Obukhov
Primo
Conceptualization
;
M. A. Brovelli
Secondo
Validation
2023

Abstract

In this research, we focused on armed conflicts and related violence. The study reviewed the use of machine learning to predict the likelihood of conflict escalation and the role of conditioning factors. The results showed that machine learning and predictive models could help identify conflict-prone locations and geospatial factors contributing to conflict escalation. The study found 46 relevant papers and emphasized the importance of considering unique predictors and conditioning factors for each conflict. It was found that the conflict susceptibility of a region is influenced principally by its socioeconomic conditions and its political/governance factors. We concluded that machine learning has the potential to be a valuable tool in conflict analysis and, therefore, it can be an asset in conflict mitigation and prevention, but the accuracy of the models depends on data quality and the careful selection of conditioning factors. Future research should aim to refine the methodology for more accurate prediction of the models.
2023
conflicts; war; conflict susceptibility; conditioning factors; predictors; machine learning
01 Pubblicazione su rivista::01a Articolo in rivista
Identifying Conditioning Factors and Predictors of Conflict Likelihood for Machine Learning Models: A Literature Review / Obukhov, T.; Brovelli, M. A.. - In: ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION. - ISSN 2220-9964. - 12:8(2023), pp. 1-22. [10.3390/ijgi12080322]
File allegati a questo prodotto
File Dimensione Formato  
Obukhov_Identifying_2023.pdf

accesso aperto

Note: https://doi.org/10.3390/ijgi12080322
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 1.41 MB
Formato Adobe PDF
1.41 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1685901
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact