prikaz prve stranice dokumenta Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca
Access restricted to students and staff of home institution
master's thesis
Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca
diplomski rad
2022. urn:nbn:hr:124:906686
Marković, Marko
University of Split
Faculty of economics Split

Cite this document

Marković, M. (2022). Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad (Master's thesis). Split: University of Split, Faculty of economics Split. Retrieved from https://urn.nsk.hr/urn:nbn:hr:124:906686

Marković, Marko. "Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad." Master's thesis, University of Split, Faculty of economics Split, 2022. https://urn.nsk.hr/urn:nbn:hr:124:906686

Marković, Marko. "Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad." Master's thesis, University of Split, Faculty of economics Split, 2022. https://urn.nsk.hr/urn:nbn:hr:124:906686

Marković, M. (2022). 'Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad', Master's thesis, University of Split, Faculty of economics Split, accessed 01 January 2025, https://urn.nsk.hr/urn:nbn:hr:124:906686

Marković M. Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad [Master's thesis]. Split: University of Split, Faculty of economics Split; 2022 [cited 2025 January 01] Available at: https://urn.nsk.hr/urn:nbn:hr:124:906686

M. Marković, "Usporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad", Master's thesis, University of Split, Faculty of economics Split, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:124:906686

Metadata
TitleUsporedba algoritama nenadziranog strojnog učenja pri segmentaciji kupaca : diplomski rad
AuthorMarko Marković
MentorŽeljko Garača (mentor)
MBZ: 148451
GranterUniversity of Split
Faculty of economics Split
Split
Defense date and country2022-09, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Segmentacija tržišta jedan je od glavnih procesa marketinga. Krajem 20. i početkom 21. stoljeća razvija se područje umjetne inteligencije i strojnog učenja. Nenadzirano strojno učenje se pokazalo kao jedna od grana koja je iznimno dobra u prepoznavanju i grupiranju uzoraka. K-Means i Hijerarhijski algoritam jedni su od najčešće korištenih algoritama u primjeni pri segmentaciji potrošača. Ovakvi algoritmi se često smatraju rezerviranim za velike baze podataka. Cilj ovog rada bio je ispitati karakteristike primjene ovakvih algoritama pri segmentaciji potrošača na manjim setovima podataka. Sukladno tomu usporediti algoritme s obzirom na rezultate segmentacije i dati odgovore na istraživačka pitanja. Pri ovom istraživanju korištena su dva seta podataka, jedan sa 500, a drugi sa 200 unosa. Svaki set sadržao je 5 varijabli. Setovi su obrađeni putem K-Means i Hijerarhijskog algoritma unutar programskog jezika Python. Primjena algoritama bila je moguća na manjim setovima podataka, ali uz kompromise u preciznosti, efikasnosti i jednostavnosti upotrebe.
Abstract (english)
Market segmentation is one of the main marketing processes. At the end of the 20th and beginning of the 21st century, the field of artificial intelligence and machine learning has greatly developed. Unsupervised machine learning has proven to be one branch that is extremely good at recognizing and grouping patterns. K-Means and the Hierarchical Algorithm are one of the most commonly used algorithms in consumer segmentation. Such algorithms are often considered to be reserved for large databases. The aim of this paper was to examine the characteristics of the application of such algorithms in consumer segmentation on smaller data sets. Accordingly, compare algorithms with respect to segmentation results and provide answers to research questions. In this research, two sets of data were used, one with 500 and the other with 200 entries. Each set contained 5 variables. The sets were processed using K-Means and the Hierarchical Algorithm within the Python programming language. Application of algorithms was possible on smaller data sets, but with compromises in precision, efficiency and ease of use.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:124:906686
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 conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2022-11-22 10:18:05