Examining generative AI and multi-dimensional drivers for sustainable development: A configurational theory approach

We investigate how configurations of technological innovation, economic drivers, governance quality, and renewable energy consumption contribute to sustainable development outcomes. Drawing on configurational theory, which suggests that the impacts of individual factors are contingent on how they are configured within systems, we employ a multi-method approach combining fuzzy-set qualitative comparative analysis (fsQCA) and artificial neural networks (ANN) across 21 countries to capture causal complexity and assess the relative influence of each condition. Analysis for 2010–2022 identifies multiple sufficient configurations that lead to high sustainable development, highlighting the critical roles of financial development, government effectiveness, supply chain digitalization, generative AI financing, and R&D. Results confirm that no single factor alone ensures sustainability; rather, tailored combinations of innovation, institutional quality, economic investment, and clean energy are required to engender sustainable development. We contribute by introducing generative AI financing as a driver, advancing the integration of machine learning with configurational methods, and offering practical insights for policymakers aiming to design multidimensional strategies for sustainable development. By identifying context-specific pathways, the findings support more adaptive and inclusive sustainability planning for both developed and developing economies.