Defense Perception in the Geopolitical Scope: An exploratory study through unsupervised machine learning

Abstract

Regarding military development worldwide, the scope of defense has influenced the economic and technological advancement of many nations, whether to defend their sovereignty or lead military power in the global geopolitical scenario. For the study in question, a database from three others is used, composed of 16 variables and 120 countries, exposing defense figures and economic and social indexes respective to each nation. In this scenario, an exploratory analysis is performed, based on statistical modeling and unsupervised machine learning techniques, exposing correlation points between the variables, listing the most influential and influenced in the evaluation scenario. Using clustering techniques through the K-means algorithm and support of the elbow graph, the possible clusters built for the defense scenario are presented, identifying a favorable number of six groups, thus listing the countries with the greatest similarities between their quantitative variables. Finally, the conclusions of the results found are presented, as well as the limitations of the study and proposals for future studies.