Razvoj sustava za autonomno trgovanje kriptovalutama

undergraduate thesis

• Title (english): Development of a system for autonomous cryptocurrency trading
• Author: Jure Salamunić
• Mentor: Hrvoje Hegeduš (mentor)
• Committee member: Hrvoje Hegeduš (predsjednik povjerenstva)
• Committee member: Petar Mostarac (član povjerenstva)
• Committee member: Roman Malarić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu cilj je bio kreirati algoritme, funkcije i uvjete koji će nas približiti pozitivnom trgovanju na tržištu kriptovaluta. Pomoću genetskih algoritama dobili smo lokalne ekstreme kao najpovoljnije točke za trgovanje, gdje su lokalni minimumi predstavljali točke kupnje, a lokalni maksimumi točke prodaje. Analizom tih točaka, probali smo se približiti funkcijama koje bi u realnom vremenu mogle prepoznati dobre prilike za trgovanje. Također smo detaljno analizirali Moving Average funkcije kao indikatore tržište te smo testirali kako bi izgledalo trgovanje kroz mjesec dana u različitim periodima za sve kombinacije križanja Moving Average-a koje smo samostalno kreirali i zadali. Testiranja smo proveli na povijesnim, ali i na realnim podatcima te dobili približno iste rezultate.

Abstract (english)

In this paper, the goal was to create algorithms, functions and conditions that will bring us closer to positive trading in the cryptocurrency market. Using genetic algorithms, we obtained local extremes as the most favorable trading points, where local minima represented points of purchase and local maxima represented points of sale. By analyzing these points, we tried to get closer to functions that could recognize good trading opportunities in real time. We also analyzed in detail the Moving Average functions as market indicators and tested what trading would look like during the month in different periods for all combinations of Moving Average crossovers that we independently created and set. We conducted testing on historical and real data and obtained approximately the same results.

• Keywords: kriptovalute; analiza tržišta; trgovanje; Moving Average; genetski algoritam; kupnja; prodaja; analiza; tržište
• Keywords (english): cryptocurrencies; market analysis; trading; Moving Average; genetic algorithm; buying; selling; analysis; market
• Language: croatian
• URN:NBN: urn:nbn:hr:168:835585
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 21:36:46