Model for identifying regions’ potential for clustering using information extraction tools and techniques

Decision-makers adopt regional industrial clusters as a development tool for competitive advantages in globalization. Identifying clustering potential within regions serves as the foundation for effective policy formulation. However, a standard systematic approach for assessing regional clustering potential is lacking. Current methods combine quantitative analyses of employment statistics to evaluate sectoral density with qualitative assessments of cluster dynamics. Advances in information technology have accelerated alongside globalization, with exponential growth in data volume and analytical capabilities. Data science processes this information for knowledge discovery, with increasing use of data mining, SQL queries, and online analytical processing (OLAP) tools in clustering analysis. This study proposes a model for detecting regional industrial clustering potential by integrating OLAP technology with data mining through an online analytical mining (OLAM) framework. This approach addresses limitations in traditional quantitative methods, such as location quotient and three-star analysis, which rely on threshold values and single regional parameters. The OLAM mechanism combines OLAP’s multidimensional analysis with data mining’s pattern recognition, thus enabling nuanced identification of clustering potential. It eliminates threshold dependencies and single-parameter evaluations, offering an alternative to conventional techniques. Integration into institutional systems can replace time-consuming traditional methods with a dynamic framework for multidimensional reporting.