Improving spatial clustering through a weight system on multilevel permanent museum attraction probability

Museums are extensively distributed all over the Italian territory. In this context, the identification of spatial patterns, referred to specific characteristics of museums evaluated at regional level, can support the enhancement of the cultural and natural heritage as well as the social and economic growth. In the literature, many studies were focused on the visitors’ profile or on the managerial performance and economic efficiency of the museums. However, none of them analysed the effects of the permanent presence of museums and their spatial contiguity by using both spatial machine learning models and statistical models. To this aim an innovative approach, which combines multilevel binary model and spatial clustering, as a machine learning unsupervised technique, is proposed to investigate the pattern recognition of the permanent museums all over the Italian territory and provide relevant information in terms of similarity among the spatial cluster formed. The logit of the museums to remain open all over the year, also with respect to different types of institution (private/public) and a different spatial/geographical constraints are jointly considered. In addition, a weight system is defined in order to introduce a regional measure of museums prevalence with respect to other types of cultural institutions. The ISTAT microdata concerning the Italian survey on museums and cultural entities are considered. The results highlight the great potentiality of this spatial clustering approach in delivering a better understanding of the role of museums as factor of challenge of urban development, providing in the meantime suggestions for tourism providers and museum managers.