Territorial Clustering Techniques for the Analysis of Tourism Sustainability in Puglia

Tourism sustainability is a key factor for regional development, especially in areas rich in natural and cultural heritage such as Apulia. This study examines the use of clustering techniques to identify spatial and temporal patterns of tourism in the region, with the aim of detecting areas subject to sustainable tourism pressure. In particular, it compares two density-based clustering algorithms: DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and HDBSCAN (Hierarchical DBSCAN). While DBSCAN is effective in identifying arbitrarily shaped clusters and handling noise, it requires empirical parameter choice and may struggle with varying data densities. HDBSCAN addresses these limitations by automatically determining the optimal cluster structure and adapting more effectively to density variations. The application of both methods to tourism data from Apulia highlights similarities and differences between the clusters, offering complementary perspectives in the analysis of sustainability.