Search academic texts

Information × Registration Number 2124U004684, Article popup.category Препринт Title popup.author Vasylevych Vlad popup.publication 01-01-2024 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4857 popup.publisher Description For a company to stay competitive, it must understand its users well and match its product to customer needs. Segmenting the user base and understanding user behavioral characteristics of each segment helps to improve the value proposition. This thesis explores three clustering algorithms - K-Means, DBSCAN, Agglomera- tive clustering, - in order to cluster users’ text dialogues of the fashion consulting mobile app LUMI. Each algorithm’s performance is assessed in terms of Silhouette score. The best-performing clustering method results are then further analysed with word frequencies to generate business insights. popup.nrat_date 2025-05-09 Close