| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Avtonomno trgovanje s kriptovalutami z uporabo nevronskih mrež : magistrsko delo
Authors:ID Kurbos, Jan (Author)
ID Šprogar, Matej (Mentor) More about this mentor... New window
Files:.pdf MAG_Kurbos_Jan_2023.pdf (3,63 MB)
MD5: 9261BED09E6FC92FA1066C64D3B30152
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Dostopnost tržnih podatkov kriptovalut predstavlja bogato podlago za uporabo nevronskih mrež za generiranje koristnih informacij za trgovanje. V magistrski nalogi smo trgovanje prevedli v problem strojnega učenja. Raziskali smo konkretne primere uporabe nevronskih mrež na področju trgovanja. Ugotovili smo, da napovedovanje tečajev ni popolna rešitev za uspešno trgovanje. Poudarili smo pomen optimizacije strategije trgovanja, ki smo jo definirali kot algoritem, ki na podlagi napovedi nevronskih mrež izvaja trgovalne akcije. Z uporabo genetskega algoritma smo strategijo uspešno prilagodili na različne pogoje trgov. Pokazali smo tudi kruto resničnost trgov, kjer se trgovanje na slepo skoraj zagotovo konča z izgubo kapitala.
Keywords:nevronske mreže, avtonomno trgovanje, trgi kriptovalut
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[J. Kurbos]
Year of publishing:2023
Number of pages:1 spletni vir (1 datoteka PDF (X, 59 f.))
PID:20.500.12556/DKUM-83832 New window
UDC:004.777:336.74(043.2)
COBISS.SI-ID:151849475 New window
Publication date in DKUM:13.03.2023
Views:708
Downloads:99
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Licensing start date:19.02.2023

Secondary language

Language:English
Title:Autonomous trading of cryptocurrencies using neural networks
Abstract:The accessibility of cryptocurrency market data provides a rich foundation for the use neural networks to generate useful information for trading. In this master's thesis, we translated trading into a machine learning problem. We explored specific examples of the usage of neural networks in trading. We found out that predicting exchange rates alone is not a complete solution for successful trading. We emphasized the importance of optimizing a trading strategy, which we defined as an algorithm that performs trading actions based on the neural network predictions. Using a genetic algorithm, we were able to adapt the strategy to different trading conditions. We also showed the harsh reality of trading, where blind trading almost certainly ends in capital loss.
Keywords:neural networks, autonomous trading, cryptocurrency markets


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica