prikaz prve stranice dokumenta POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA
  Download
PDF 2.27 MB
master's thesis
POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA
Diplomski rad
2018. urn:nbn:hr:124:937390
Birgmajer, Petar
University of Split
Faculty of economics Split

Cite this document

Birgmajer, P. (2018). POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad (Master's thesis). Split: University of Split, Faculty of economics Split. Retrieved from https://urn.nsk.hr/urn:nbn:hr:124:937390

Birgmajer, Petar. "POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad." Master's thesis, University of Split, Faculty of economics Split, 2018. https://urn.nsk.hr/urn:nbn:hr:124:937390

Birgmajer, Petar. "POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad." Master's thesis, University of Split, Faculty of economics Split, 2018. https://urn.nsk.hr/urn:nbn:hr:124:937390

Birgmajer, P. (2018). 'POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad', Master's thesis, University of Split, Faculty of economics Split, accessed 12 February 2025, https://urn.nsk.hr/urn:nbn:hr:124:937390

Birgmajer P. POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad [Master's thesis]. Split: University of Split, Faculty of economics Split; 2018 [cited 2025 February 12] Available at: https://urn.nsk.hr/urn:nbn:hr:124:937390

P. Birgmajer, "POTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad", Master's thesis, University of Split, Faculty of economics Split, Split, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:124:937390

Metadata
TitlePOTENCIJAL ANALIZE KORISNIČKIH PODATAKA WEB SERVISA ZA RECENZIRANJE USLUGA : Diplomski rad
AuthorPetar Birgmajer
MentorMaja Ćukušić (mentor)
MBZ: 300571
GranterUniversity of Split
Faculty of economics Split
Split
Defense date and country2018-08, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
U današnjem svijetu, gotovo da i ne postoji poduzeće koje ne koristi podatke u svrhu unaprjeđenja poslovanja, pa stoga i ne čudi kako se upravo podaci smatraju najvrjednijim resursom današnjice. Podaci u svom sirovom obliku ne predstavljaju vrijednost za poduzeće, stoga kako bi se iskoristio njihov potencijal, potrebno je primijeniti odgovarajuće tehnike rudarenja podataka. Poslovna inteligencija kao koncept objedinjuje strategije i tehnologije korištene od strane poslovnih subjekata za analizu poslovnih podataka, s rudarenjem podataka kao jednom sastavnih funkcija. CRISP-DM predstavlja najpopularniji metodološki okvir za provođenje projekata rudarenja podataka, a sastoji se od 6 faza koje uključuju razumijevanje poslovnog problema, razumijevanje podataka, pripremu podataka, modeliranje, evaluaciju modela te isporuku odnosno implementaciju rezultata. Klasifikacija kao tehnika rudarenja podataka biti će, uz praćenje CRISP-DM metodološkoga okvira primijenjena na setu podataka web servisa za recenziranje usluga Yelp, a biti će evaluirani i različiti klasifikacijski algoritmi.
Abstract (english)
In today's world, it is almost impossible to find a business that does not utilitze data in order to enhance its performance, therefore it is no wonder data is regarded as the most valuable resource to a company. Data in its raw form does not provide value to its owner, accordingly, an appropriate set of techniques has to be applied in order to exploit its potential. Business intelligence (BI) comprises the strategies and technologies used by enterprises for the data analysis of business information, with data mining as one of its essential functions. CRISP-DM represents the most widely used structured approach for planning and execution of a data mining project. CRISP-DM methodology consists of six phases, including business understanding, data understanding, data preparation, modeling, evaluation and deployment. Following CRISP-DM methodology framework, classification techniques are applied on a dataset consisted of reviews from Yelp user review platform, together with a performance evaluation of various classification algorithms.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:124:937390
Study programmeTitle: Business Studies
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra ekonomije (magistar/magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-12-07 10:40:09