Clustering-Based Optimized Site Selection

Site location has always been an important part of every industry and a highly researched aspect of operation research. If selected properly, costs and profit would benefit the institute. Site selection depends on many factors, such as population, laws, vegetation, etc. For site selection, various constraints need to be satisfied such as transportation cost and maintenance costs. The model infers not only population density but amenities nearby such as hospitals and metro stations. In this study, we propose a clustering-based machine learning approach to shortlist the potential sites for any kind of facility for which site selection is needed. The model relies on data provided by a database like OpenStreetMap for site selection. The site locations produced by the model are cross verified by comparing their location with similar positions in each cluster and are ranked accordingly. The model has been deployed and tested in various locations, primarily the Indian metropolitan cities.