The occurrence dataset for Neobuccinum eatoni was compiled through filtration process, starting with records from the Global Biodiversity Information Facility (GBIF) and supplemented by museum specimens and additional sources like SOMBASE, iBOL, NIWA, ANTABIF, and SCAR-AntOBIS. Further data were sourced from the National Museum of Natural History in Paris, the University of Vigo, and recent fieldwork in Antarctica, Heard Island, and Kerguelen Island. Records were meticulously screened to remove misidentified specimens, inaccurate locations, duplicates, and outdated entries, ensuring accuracy and relevance. To address spatial autocorrelation, clustering methods divided the data into distinct geographic clusters, producing a refined dataset used to model N. eatoni's potential distribution with enhanced predictive reliability by reducing spatial autocorrelation effects.