magistrsko delo
Marko Ambrožič (Author), Igor Kononenko (Mentor)

Abstract

V delu je predstavljen primer pristopa za napovedovanje gibanja cen kriptovalut. Uporabljena je bila podatkovna množica štirih trgovalnih parov USDT BTC, USDT LTC, USDT ETH in USDT XRP, ki je bila pridobljena preko programskega vmesnika kriptoborze Poloniex. Pristop s prevedbo na razrede kupi, prodaj in drži ter uporabo napredne tehnične analize se je v kombinaciji z naprednimi arhitekturami nevronskih mrež izkazal za uspešnega, z boljšimi končnimi rezultati in nižjim standardnim odklonom kot samo držanje kriptovalute. Poleg tega, je eden glavnih prispevkov tega dela primerjava različnih strategij trgovanja v kombinaciji z nevronskimi mrežami. Primerjane so tri strategije trgovanja, in sicer intervalno trgovanje, trendovsko trgovanje in trgovanje z deležem sredstev. Za najbolj uspešno se je izkazalo intervalno trgovanje z določanjem minimalnih in maksimalnih vrednosti znotraj 24 urnega intervala. Predstavljeno je tudi modularno ogrodje, implementirano med raziskovanjem, ki lahko služi kot orodje za hitro preverjanje različnih strategij in pristopov. Uporabljene so bile rekurenčne nevronske mreže in nevronske mreže z dolgim kratkoročnim spominom.

Keywords

kriptovalute;strojno učenje;algoritmično trgovanje;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [M. Ambrožič]
UDC: 004.8:336.74(043.2)
COBISS: 40924675 Link will open in a new window
Views: 1075
Downloads: 235
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Predicting the price movements of Bitcoin and other cryptocurrencies
Secondary abstract: We showed a possible approach to predicting the movement of prices of cryptocurrencies. We used a data set of four trading pairs USDT BTC, USDT LTC, USDT ETH, and USDT XRP, gathered through the public api of the cryptocurrency exchange Poloniex. The translation of the problem to three possible trading actions buy, sell and hold as well as an advanced technical analysis in combination with advanced neural net architectures was shown as successful with a better final outcome and lower standard deviation than just buying and holding the currency. Apart from this one of the main contributions is a comparison of different trading strategies in combination with the usage of neural nets. A comparison was made of three different trading strategies. These are interval trading, trend trading and trading with only a part of the assets. An approach of finding the minimum and maximum values in a given 24 hour interval, called interval trading, was shown as the most successful. We also introduce a modular framework that was implemented during research and can be used as a quick way to check different strategies and approaches. We used recurrent and long-short term memory neural networks.
Secondary keywords: cryptocurrency;machine learning;algorithmic trading;computer science;computer and information science;master's degree;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 68 str.
ID: 12189495