Oritsemeyiwa Gabriel Orugboh, United Kingdom

The accelerating digitalization of society has produced massive volumes of social, economic, and behavioural data, creating opportunities to transform social policy from reactive to predictive. Traditional frameworks, constrained by slow data cycles and fragmented records, fail to capture complex societal dynamics. This paper outlines a computational sociology methodology that employs big data analytics and predictive modelling to support data-driven policy design social policy. Using open government data, social media, and census records, unsupervised clustering and regression modelling identify patterns of digital exclusion, income disparity, and urban vulnerability. Comparative case studies of Nigeria’s Conditional Cash Transfer Program and Kenya’s Hunger Safety Net Programme demonstrate that algorithmic targeting enhances accuracy, responsiveness, and transparency. Results show targeting precision improvements of over 30% and decision lag reductions up to 80%. The study proposes a decision-support dashboard with explainable AI to advance ethical, inclusive, and adaptive policy governance.

Big Data Analytics, Computational Sociology, Evidence-Based Policy, Machine Learning, Social Inequality, Smart Governance,