What kind of 'world order'? An artificial neural networks approach to intensive data mining

•We use a minimal dataset of 5 public indicators for year 2007 and 118 countries.•We use an ACS ANN architecture to reconstruct the patterns of alliances and conflicts.•For democracies, the networks of relations display full allies/enemies gradations.•For authoritarian countries, networks of allies/enemies relations are sharply binary.•Our findings favor a Democratic Peace perspective over a Clash of Civilizations one.

In this paper, we present an innovative data processing architecture, the Activation & Competition System (ACS), and show how this methodology allows us to reconstruct in detail some aspects of the fine grained structure of global relationships in the world order perspective, on the basis of a minimal dataset only consisting of the values of five publicly available indicators for 2007 for the 118 countries for which they are jointly available. ACS seems in particular to qualify as a valuable tool for the analysis of inter-country patterns of conflict and alliances, which may prove of special interest in the current situation of global strategic uncertainty in international relations.