Analiza korisničkih podataka na internetskim platformama primjenom algoritama grupiranja

master's thesis

• Title (english): User Data Analysis on Internet Platforms Using Clustering Algorithms
• Author: Lovre Šimundić
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-04, Croatia

Abstract

Ovaj diplomski rad istražuje primjenu algoritama grupiranja za analizu korisničkih podataka na internetskim platformama, s naglaskom na web analitiku i analitiku financijskih platformi. Teorijski dio obuhvaća povijest razvoja ovih dviju analitika, ključne pojmove, najčešće korištene alate i sl. Isto tako, teorijski dio opisuje algoritme grupiranja kao što su K-means, DBSCAN, hijerarhijsko grupiranje i model Gaussovih mješavina. Praktični dio uključuje analizu podataka internetske trgovine i korisnika kreditnih kartica, korištenjem različitih algoritama grupiranja. Rezultati pokazuju da pravilna primjena ovih algoritama može poboljšati segmentaciju korisnika i optimizaciju poslovnih procesa.

Abstract (english)

This thesis explores the application of clustering algorithms for analyzing user data on internet platforms, with a focus on web analytics and financial platform analytics. The theoretical section covers the history of the development of these analytics, key concepts, and the most commonly used tools. It also describes clustering algorithms such as K-means, DBSCAN, hierarchical clustering, and Gaussian mixture models. The practical section includes the analysis of e-commerce data and credit card users, using various clustering algorithms. The results show that proper application of these algorithms can enhance user segmentation and optimize business processes.

• Keywords: grupiranje; algoritmi grupiranja; nenadzirano učenje; web analitika; analitika internet trgovina; financijska analitika; analitika kreditnih kartica; k-means; DBSCAN; aglomerativno grupiranje; model Gaussovih mješavina; PCA; korisnički podaci; segmentacija korisnika
• Keywords (english): clustering; clustering algorithms; unsupervised learning; web analytics; e-commerce analytics; financial analytics; credit card analytics; K-means; DBSCAN; agglomerative clustering; Gaussian mixture models; PCA; user data; user segmentation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:971661
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-12 22:15:27