Multilateral interventions through United Nations Peace Support Operations (PSOs) are key international responses in contexts where there is prolonged intra-State and inter-State armed conflict. Understanding the effectiveness of PSOs, in reducing both national conflict and the spread of conflict across national borders, is critical in improving the capacity of States and international actors to tailor targeted response plans and reduce the risk of violence. Recent years have seen rapid development of new technologies, such as machine learning models that enable the identification of informative patterns from large amounts of information.
This Working Paper aims to cover a critical methodological gap by testing the utility of machine learning in identifying potential correlations between PSO personnel characteristics, and national and cross-border stability dynamics.