prikaz prve stranice dokumenta Predviđanje cijena kriptovaluta primjenom dubokog učenja
Access restricted to authenticated users
undergraduate thesis
Predviđanje cijena kriptovaluta primjenom dubokog učenja
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:906509
Milković, Toni
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Milković, T. (2022). Predviđanje cijena kriptovaluta primjenom dubokog učenja (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:906509

Milković, Toni. "Predviđanje cijena kriptovaluta primjenom dubokog učenja." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:906509

Milković, Toni. "Predviđanje cijena kriptovaluta primjenom dubokog učenja." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:906509

Milković, T. (2022). 'Predviđanje cijena kriptovaluta primjenom dubokog učenja', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 02 December 2024, https://urn.nsk.hr/urn:nbn:hr:179:906509

Milković T. Predviđanje cijena kriptovaluta primjenom dubokog učenja [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 December 02] Available at: https://urn.nsk.hr/urn:nbn:hr:179:906509

T. Milković, "Predviđanje cijena kriptovaluta primjenom dubokog učenja", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:906509

Metadata
TitlePredviđanje cijena kriptovaluta primjenom dubokog učenja
Title (english)Cryptocurrency prices prediction using deep learning
AuthorToni Milković
MentorMatko Šarić https://orcid.org/0000-0001-9752-9653 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Tema ovog završnog rada bila je provjeriti može li se korištenjem strojnog učenja predvidjeti cijena Bitcoin kriptovalute. Početak rada daje kratki pregled strojnog učenja i opisuje funkcionalnost konvolucijskih neuralnih mreža. Predstavljena su dva modela, ResNet i GoogLeNet model konvolucijskih mreža i dva slučaja koja smo odlučili testirati. Oba modela testirali smo u slučaju kada ih treniramo na svijećnom grafu od 24 svijeće s jednim vremenskim intervalom i na skupu svijećnih grafova s više vremenskih intervala i 6 svijeća po grafu. Objasnili smo način prikupljanja podataka za treniranje i testiranje mreža te generiranje potrebnih grafova. Prikazali smo rezultate točnosti pojedinih modela za svaki slučaj i zaključili da samo u jednom slučaju model postiže točnost bolju od nasumičnog pogađanja.
Abstract (english)
The topic of this thesis was to test if using machine learning can help us predict future bitcoin prices. The thesis covers a brief introduction to the topic of machine learning as well as convolutional networks and certain popular models, ResNet and GoogLeNet. We train both models on two candlestick charts, one with 24 candles in 1 hour intervals, and one with 6 combined charts with 6 candles each in different timeframes. We explain the data collection and chart generation process and show that most models have an accuracy of 50%. Only one model had an accuracy that was significantly better than random guessing.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:906509
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-06-09 10:54:04