prikaz prve stranice dokumenta Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.
Access restricted to students and staff of home institution
master's thesis
Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics in Osijek, 2019. urn:nbn:hr:145:446598
Galjar, Dominik
Josip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
Chair of Quantitative Methods and Informatics

Cite this document

Galjar, D. (2019). Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina. (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:145:446598

Galjar, Dominik. "Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:145:446598

Galjar, Dominik. "Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:145:446598

Galjar, D. (2019). 'Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, accessed 21 January 2025, https://urn.nsk.hr/urn:nbn:hr:145:446598

Galjar D. Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina. [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek; 2019 [cited 2025 January 21] Available at: https://urn.nsk.hr/urn:nbn:hr:145:446598

D. Galjar, "Model strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:145:446598

Please login to the repository to save this object to your list.
Metadata
TitleModel strojnog učenja za predviđanje kriptovaluta na primjeru bitcoina.
Title (english)Machine learning model for cryptocurrency predictions on example of bitcoin
AuthorDominik Galjar
MentorMarijana Zekić Sušac (mentor)
Committee memberMarijana Zekić Sušac (predsjednik povjerenstva)
Committee memberJosip Mesarić (član povjerenstva)
Committee memberMartina Briš Alić (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 country2019-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Bitcoin je u zadnje desetljeću privukao značajnu pažnju u poljima poput ekonomije, kriptografije i računalne znanosti zbog svoje prirode kombiniranja enkripcijske tehnologije i monetarnih jedinica. Ovaj rad prikazuje i objašnjava početak i razvoj bitcoina od njegovih najranijih dana kada se još nije ni koristio niti bio prihvaćen kao relevantno sredstvo razmjene pa sve do njegovih „najslavnijih“ dana kada je postigao astronomski velike cijene. U radu je razvijen model za predviđanje budućih cijena bitcoina na temelju podataka iz prošlosti pomoću neuronski mreža, točnije regresijskog modela koji će procijeniti kontinuiranu vrijednost izlazne varijable odnosno cijene bitcoina za idući dan. Rezultati razvijenog modela pokazali su da diferenciranjem podataka i korištenjem tanges hiperbolne funkcije dobivamo veću stopu točnosti odnosno veću korelaciju koja je iznosila 0.809.
Abstract (english)
Bitcoin has attracted considerable attention in the last decade in the fields such as economics, cryptography and computer science because of its nature of combining encryption technology and monetary units. This paper summarizes and explains the development of bitcoin since its early days when it wasn't even accepted as relevant means of exchange, all the way to its “glory days when it reached astronomical prices. A model is developed in this paper to predict future prices of bitcoin based on historical data with use of neural networks, specifically with regression model which will estimate a continuous value of an output variable which is the price of bitcoin for the next day. The result of the created neural network model shows us that with the usage of differentiated data and tanges hyperbolicus function we get more reliable results and greater correlation rate which was 0.809.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:145:446598
Study programmeTitle: Business economy; specializations in: Business Informatics
Course: Business Informatics
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
RepositoryEFOS REPOSITORY
Created on2019-07-17 11:10:20