Predviđanje ponašanja korisnika temeljem obavijesti o događaju

master's thesis

• Title (english): Predicting of User Behavior Based on Event Notification
• Author: Bruno Jagić
• Mentor: Dragan Jevtić (mentor)
• Committee member: Dragan Jevtić (predsjednik povjerenstva)
• Committee member: Ognjen Dobrijević (član povjerenstva)
• Committee member: Marina Bagić Babac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu prikazani su principi dohvaćanja, čišćenja, transformiranja, normalizacije i filtriranja podataka u svrhu pripreme za prediktivnu analizu. Prilikom čišćenja podataka nad istima se provodi analiza te se prikuplja znanje o njima kako bi se prediktivnom dijelu projekta moglo pristupiti što bolje i preciznije. Sljedeći korak u izgradnji prediktivnog modela su odabir i implementacija algoritma. Postoji nekoliko pristupa izgradnji prediktivnog modela, a u ovom radu fokus je stavljen na algoritme za nadzirano učenje jer u setu podataka postoji varijabla čiju je vrijednost potrebno predvidjeti.

Abstract (english)

In this document there have been shown principles of data fetching, cleansing, transformation, normalization and filtering in order to prepare it for predictive analysis. This processes give the chance for data analysis in order to collect knowledge about it and enable developers to prepare best algorithm for this data to get most efficient and solution. Next step in this process is implementation of predictive analysis algorithm and it is necessary to choose best fit and build right algorithm. This document is based on algorithms for supervised learning because in data there is one dependant variable which value needs to be guessed.

• Keywords: prediktivna analiza; nadzirano učenje; logistička regresija; neuronska mreža; čišćenje podataka; obrada podataka
• Keywords (english): predictive analysis; supervised learning; logistic regression; neural network; data cleansing; data transformation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:609982
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 09:21:10