Na tehničkoj analizi zasnovano algoritamsko trgovanje

master's thesis

• Title (english): Technical analysis based algorithmic trading
• Author: David Konjevod
• Mentor: Damir Seršić (mentor)
• Committee member: Damir Seršić (predsjednik povjerenstva)
• Committee member: Ana Sović Kržić (član povjerenstva)
• Committee member: Juraj Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-11, Croatia

Abstract

Ovaj diplomski rad fokusira se na razvoj algoritama za donošenje odluka u algoritamskom trgovanju temeljenih na tehničkoj analizi. Cilj je implementirati algoritam koji može analizirati, obraditi i izdvojiti značajke iz financijskih vremenskih nizova kako bi se donosile informirane odluke u trgovanju. Studija uspoređuje klasične strategije trgovanja temeljene na pravilima s modernim pristupima koji uključuju algoritme strojnog učenja, konkretno pokušavajući primijeniti model transformatora na financijske nizove podataka. Rad ocjenjuje ove modele testiranjem na neovisnim skupovima financijskih podataka kako bi se osigurala pouzdanost i mogućnost generalizacije u stvarnim uvjetima trgovanja.

Abstract (english)

This thesis focuses on the development of decision-making algorithms in algorithmic trading based on technical analysis. The objective is to implement an algorithm capable of analyzing, processing, and extracting features from financial time series to make informed trading decisions. The study compares classical rule-based trading strategies with modern approaches that incorporate machine learning algorithms, specifically attempting to apply the transformer model to financial time series data. The work evaluates these models by testing them on independent sets of financial data to ensure reliability and the ability to generalize in real trading conditions.

• Keywords: Algoritamsko trgovanje; tehnička analiza; financijski vremenski nizovi; strategije trgovanja; modeli temeljeni na pravilima; RSI; SMA; transformator; koder; dekoder; strojno učenje
• Keywords (english): Algorithmic trading; technical analysis; financial time series; trading strategies; rule-based models; RSI; SMA; transformer; encoder; decoder; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:684507
• 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: 2024-10-12 21:06:45