Search academic texts

Information × Registration Number 2123U006676, Article popup.category Препринт Title popup.author Sliusarchuk Khrystyna popup.publication 01-01-2023 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4821 popup.publisher Description Given the current competition in the mobile application market, a deep and clear understanding of the users, their goals and pains, is crucial. Based on the demo- graphic and behavioral characteristics of the users, the segmented user base helps the company to tailor its strategy to reach the right users with the right messages, prices, and products. This thesis explores and points out the virtues and vices of the most widespread unsupervised machine learning clustering algorithms including k-means, agglomerative clustering, and DBSCAN, in order to cluster the user base of the iOS and Android leading mobile application in the horoscope and astrology market. The clustering results for each of the algorithms are assessed and compared in terms of the Silhouette score. The results of the best-performing clustering al- gorithm are interpreted with individual business recommendations developed for each. popup.nrat_date 2025-05-09 Close