prikaz prve stranice dokumenta Implementacija sustava za preporučivanje stručnjaka
No public access
master's thesis
Implementacija sustava za preporučivanje stručnjaka
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:126956
Topolovac, Iva
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Topolovac, I. (2019). Implementacija sustava za preporučivanje stručnjaka (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:126956

Topolovac, Iva. "Implementacija sustava za preporučivanje stručnjaka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:126956

Topolovac, Iva. "Implementacija sustava za preporučivanje stručnjaka." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:126956

Topolovac, I. (2019). 'Implementacija sustava za preporučivanje stručnjaka', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 August 2024, https://urn.nsk.hr/urn:nbn:hr:168:126956

Topolovac I. Implementacija sustava za preporučivanje stručnjaka [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 August 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:126956

I. Topolovac, "Implementacija sustava za preporučivanje stručnjaka", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:126956

Metadata
TitleImplementacija sustava za preporučivanje stručnjaka
Title (english)Implementation of a recommender system for finding experts
AuthorIva Topolovac
MentorMarko Jurčević (mentor)
Committee memberMarko Jurčević (predsjednik povjerenstva)
Committee memberRoman Malarić (član povjerenstva)
Committee memberŽeljka Car (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Osnovna podjela sustava za preporučivanje uključuje preporučivanje na temelju suradnje korisnika te preporučivanje temeljem sadržaja. Dok su preporučitelji temeljeni na suradnji korisnika fokusirani na sličnosti među korisnicima ili stavkama, preporučivanje temeljem sadržaja gradi korisničke profile na temelju značajki stavke. Oba sustava imaju svoje prednosti i nedostatke, a mogu se i kombinirati u svrhu postizanja besprijekorne preporuke. U nautičkoj domeni pojavila se potreba za jednim takvim sustavom čija bi svrha bila preporučivanje voditelja brodice prema preferencijama gosta - iznajmljivača plovila, prilikom nautičkog putovanja. S tim ciljem razvijena je aplikacija SkipperBooking koja služi kao platforma za povezivanje gosta i voditelja brodice. Algoritam preporučivanja voditelja brodice kombinira preporučivanje temeljem suradnje korisnika te metode za ublažavanje cold start problema. Za razliku od sličnih postojećih aplikacija, SkipperBooking omogućuje obostrano zadovoljstvo angažmanom jer pruža visoku razinu osobne podudarnosti gosta i voditelja brodice.
Abstract (english)
Recommender systems usually make use of either collaborative filtering or content-based filtering. While the collaborative filtering algorithms focus on similarities between users or items, content-based filtering algorithms create user profiles based on item descriptions. Both systems have weaknesses and strengths and can be combined in order to give an impeccable recommendation. In the nautical domain, a need has emerged for such a system whose purpose would be to recommend a skipper that matches guest’s preferences for a sailing voyage. With this in mind, SkipperBooking application has been developed as a platform for connecting guests and skippers. The algorithm for recommending skippers combines collaborative filtering and methods for mitigating the cold start problem. Unlike similar existing applications, SkipperBooking offers a mutual satisfaction as it makes sure there is a perfect fit bewteen the guest and the skipper.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:126956
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 22:42:18