Answers are grounded in this paper and cite their sources.
Analysis identifies convergence clubs in European regions, suggesting innovation drives economic development.
This article contributes to a better understanding of the convergence behavior of European regions and provides recommendations on how to effectively promote accelerated economic development. We first identify convergence clubs among EU NUTS-2 regions, then determine the characteristics that drive regions into specific clubs, and subsequently provide an in-depth analysis of the empirical interrelations of these characteristics at the individual region level to lay the foundation for predicting how regions can escape their current convergence regimes. To this end, we employ the log- t test to identify four convergence clubs based on per-capita GVA. To understand these club affiliations, we use the novel non-parametric estimator, Ordered Random Forest (ORF) . Finally, we apply innovative tools from interpretable machine learning to derive in-depth insights from the model and identify threshold values that trigger shifts in predicted convergence club membership, both on average and for each individual region. Our findings suggest the overwhelming importance of technological readiness and innovation in boosting regional convergence.
No takes yet. Share an insight, caveat, or question.
Zwerschke et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: