Global world (dis-)order? Analyzing the dynamic evolution of the micro-structure of multipolarism by means of an unsupervised neural network approach


•We propose a nonlinear approach to the analysis of the world order.
•We build on a machine learning approach based upon the Auto-CM architecture.
•Apparently minor countries may have a big role in the shaping and evolution of the world order.
•Latin American and Caribbean countries play a more important role than usually maintained.
•Computational approaches to scenario creation and analysis in international relations have great potential