Research & Studies

Combining spatial and aspatial methods to identify European industrial leagues

Summary

Zsolt T. Kosztyán, Head of Research is a co-author of a brand new scientific article. This study was released in Heliyon in 2026.

Zsolt T. Kosztyán, Head of Research is a co-author of a brand new scientific article. This study was released in Heliyon with the title of Combining spatial and aspatial methods to identify European industrial leagues: Development perspectives.

Absrtact

This study addresses a critical need in regional development planning by combining aspatial biclustering with spatial autocorrelation analysis to examine European industrial competitiveness. Focusing on NUTS 2 regions, we move beyond broad categorizations by identifying data-driven “industrial leagues”—clusters of regions with similar strengths and weaknesses across 71 retained Industry 4.0 (I4.0)+ readiness indicators covering 320 regions. The proposed approach groups regions with similar economic and technological characteristics and then evaluates the spatial dependence of the resulting patterns. The analysis identifies seven regional leagues, each characterized by specific strengths and development challenges. For example, regions in Western Europe, such as Inner London–West and Brussels, exhibit high employment-based I4.0+ indicator values, whereas regions including Bucharest and Bratislava exhibit weaknesses in Research and Development (R&D) and workforce skills. Regional adoption conditions, including infrastructure quality and sectoral specialization, are associated with I4.0 readiness. The methodology also identifies sectoral concentrations within leagues, such as automotive manufacturing in Germany and ICT in Ireland, with implications for targeted development policy. Some regional groups combine strong employment indicators with weaker science-and-technology and R&D indicators, indicating a need for targeted investment in research infrastructure. Other groups share weak media-presence indicators and may require broader intervention. By identifying the indicators most closely associated with each league, this study provides policy-makers with evidence for tailored strategies that combine location-based and sector-specific measures.

Keywords: Industrial clusters, Biclustering analysis, Spatial autocorrelation, Regional development, Industry 4.0, European regional analysis, Technological specialization, NUTS 2 regions

The article with full text is available HERE.