prikaz prve stranice dokumenta Model za predviđanje cijena dionica pomoću metoda strojnog učenja
  Download
PDF 1.21 MB
master's thesis
Model za predviđanje cijena dionica pomoću metoda strojnog učenja
Diplomski rad
2024. urn:nbn:hr:145:130760
Iljić, Luka
Josip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
Chair of Quantitative Methods and Informatics

Cite this document

Iljić, L. (2024). Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:145:130760

Iljić, Luka. "Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:145:130760

Iljić, Luka. "Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:145:130760

Iljić, L. (2024). 'Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, accessed 27 January 2025, https://urn.nsk.hr/urn:nbn:hr:145:130760

Iljić L. Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek; 2024 [cited 2025 January 27] Available at: https://urn.nsk.hr/urn:nbn:hr:145:130760

L. Iljić, "Model za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:145:130760

Please login to the repository to save this object to your list.
Metadata
TitleModel za predviđanje cijena dionica pomoću metoda strojnog učenja : Diplomski rad
Title (english)A model for forecasting stock prices using machine learning methods : Graduate paper
AuthorLuka Iljić
MentorDomagoj Ševerdija (mentor)
MentorAdela Has (komentor)
Committee memberMartina Briš (predsjednik povjerenstva)
Committee memberDomagoj Ševerdija (član povjerenstva)
Committee memberDario Šebalj (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
(Chair of Quantitative Methods and Informatics)
Osijek
Defense date and country2024-09-30, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Umjetna inteligencija je pojam koji se sve češće spominje u zadnjih desetak godina, gotovo da ne postoji osoba koja nije čula ili se pak susrela s tim pojmom. U posljednje vrijeme sve se više daje na važnosti umjetnoj inteligenciji i njenom razvoju. U razvoju umjetne inteligencije važnu ulogu ima strojno učenje. Metode strojnog učenja se uveliko primjenjuju u raznim područjima poznatima čovjeku. Od primjene u medicini, obrazovanju, proizvodnji pa sve do zabavne industrije. Tako se umjetna inteligencija učestalo koristi u brojnim ekonomskim područjima, npr. za predviđanje rizika, predviđanje cijena određenih proizvoda, predviđanje cijena dionica i slično. Zato se moderna i tehnološki orijentirana poduzeća uvelike okreću primjeni i unaprjeđenju umjetne inteligencije kako bi što brže i efikasnije predvidjele i minimizirale rizike, te lakše prepoznale prilike koje se pružaju u okolini koja svakim danom postaje sve dinamičnija. U ovom radu bit će prikazan povijesni razvoj strojnog učenja, metode koje se koriste i duboko učenje. Zatim će biti objašnjene metode strojnog učenja poput logičke regresije, neuronskih mreža i k-najbližih susjeda, te će se na temelju dobivenih rezultata pokušati utvrditi koja metoda je najbolja za predviđanje cijena dionica. Analiza i modeliranje će biti izvršeni uz pomoć programskog alata Python.
Abstract (english)
Artificial intelligence is a term that has been mentioned more and more often in the last ten years, there is hardly a person who has not heard or encountered this term. Recently, more and more attention has been given to artificial intelligence and its development. Machine learning plays an important role in the development of artificial intelligence. Machine learning methods are widely applied in various fields known to man. From application in medicine, education, production to the entertainment industry. Thus, artificial intelligence is often used in a number of economic fields, for example, for predicting risks, predicting the prices of certain products, predicting stock prices, and the like. That is why modern and technologically oriented companies are largely turning to the application and improvement of artificial intelligence in order to predict and minimize risks as quickly and efficiently as possible, and to more easily recognize the opportunities offered in an environment that is becoming more and more dynamic every day. In this paper, the historical development of machine learning, the methods used and deep learning will be presented. Then, machine learning methods such as logical regression, neural networks and k-nearest neighbors will be explained, and based on the obtained results, an attempt will be made to determine which method is the best for predicting stock prices. Analysis and modeling of the project will be performed with the help of the Python programming tool.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:145:130760
Study programmeTitle: Business economy; specializations in: Financial management, Management, Entrepreneurship and innovation, Marketing, Business informatics, Supply chain management
Course: Business informatics
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni magistar /magistra ekonomije (sveučilišni magistar /magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2025-01-22 13:08:09