prikaz prve stranice dokumenta Sustav za preporuku pjesama na temelju korisničkih ocjena
No public access
master's thesis
Sustav za preporuku pjesama na temelju korisničkih ocjena
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:488415
Peš, Lucijan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Peš, L. (2019). Sustav za preporuku pjesama na temelju korisničkih ocjena (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:488415

Peš, Lucijan. "Sustav za preporuku pjesama na temelju korisničkih ocjena." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:488415

Peš, Lucijan. "Sustav za preporuku pjesama na temelju korisničkih ocjena." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:488415

Peš, L. (2019). 'Sustav za preporuku pjesama na temelju korisničkih ocjena', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:488415

Peš L. Sustav za preporuku pjesama na temelju korisničkih ocjena [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 November 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:488415

L. Peš, "Sustav za preporuku pjesama na temelju korisničkih ocjena", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:488415

Metadata
TitleSustav za preporuku pjesama na temelju korisničkih ocjena
Title (english)Song recommender system based on user ratings
AuthorLucijan Peš
MentorMarin Vuković (mentor)
Committee memberMarin Vuković (predsjednik povjerenstva)
Committee memberDragan Jevtić (član povjerenstva)
Committee memberMiljenko Mikuc (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu su opisane vrste sustava za preporuku sadržaja te su istražena i opisana postojeća rješenja sustava za preporuku pjesama na temelju njihovog sadržaja. Obrađene su metode latentne reprezentacije i redukcije dimenzionalnosti ulaznih podataka. Kao rezultat istraživanja predstavljen je i implementiran novi sustav preporuka na temelju sadržaja pjesama. Za određivanje pripadnosti pjesama pojedinim kategorijama koristio se algoritam gradient boosting koji se pokazao efektivnim pri učenju nad malim brojem primjera s velikim brojem značajki. Objektivnom i subjektivnom analizom rezultata pokazalo se kako modelirani sustav uspješno gradi liste pjesama koje uvelike odgovaraju korisničkim upitima te poboljšavaju korisničko iskustvo.
Abstract (english)
This paper goes through different types of content recommendation systems and explores existing content-based music recommender systems. Different latent representation methods and dimensionality reduction techniques of input data were presented. As a result of the research, a new content-based music recommender system was introduced and implemented. To determine the affiliation of songs to particular categories, a gradient boosting algorithm was used which proved to be effective in case of a small number of examples with a large number of features. Objective and subjective analysis of the results showed that the modeled system successfully builds song playlists that largely respond to user queries and improves overall user experience.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:488415
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2020-01-07 21:16:09