Algoritamsko trgovanje koristeći neuronske mreže

master's thesis

• Title (english): Algorithmic trading using neural networks
• Author: Matej Pipalović
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: Marko Đurasević (član povjerenstva)
• Committee member: Jan Šnajder (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Algoritamsko trgovanje oblik je trgovanja vrijednosnicama koji samostalno izvršava istrukcije i prethodno definirane strategije u realnom vremenu. Pri tome koristi javno dostupne informacije o cijeni i volumenu. U algoritamskom trgovanju često se koriste kompleksne formule kombinirane s matematičkim modelima i osobnim iskustvom kako bi se donesle odluke o kupnji i prodaji vrijednosnica. U ovom su radu u svrhu donošenja tih odluka korištene neuronske mreže, jer uz pomoć njih nužno potrebno modelirati neke aspekte strategija koji zahtjevaju znanje specifično za domenu.

Abstract (english)

Algorithmic trading is a form of securities trading that independently executes instructions and previously defined strategies in real-time. In doing so, it uses publicly available information on price and volume. In algorithmic trading, complex formulas combined with mathematical models and personal experience are often used to make decisions about buying and selling securities. In this paper, neural networks were used for the purpose of making these decisions, because by using them, it's not necessary to model some aspects of strategies that require domain-specific knowledge.

• Keywords: algoritamsko trgovanje; trgovanje; dionice; indikatori; grafovi; tehnička analiza; neuronske mreže; dnn; lstm
• Keywords (english): algorithmic trading; trading; stocks; indicators; graphs; techincal analysis; neural networks; dnn; lstm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:854211
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:29:53