Algoritamsko trgovanje financijskim instrumentima zasnovano na analizi vremenskih serija

undergraduate thesis

• Title (english): Algorithmic Trading of Financial Instruments Based On Time Series Analysis
• Author: Lovre Šimundić
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Vlaić (član povjerenstva)
• Committee member: Ivan Mikulić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Cilj ovog završnog rada bio je programski ostvariti automatiziranu strategiju trgovanja
financijskim instrumentima na osnovi analize vremenskih serija. Vremenske serije su se analizirale statističkim metodama odnosno tehničkim indikatorima. Proučene su i opisane strategije algoritamskog trgovanja, kao i statističke metode na kojima se temelji procjena kretanja cijene financijskog instrumenta. Isto tako, razrađeni su osnovni principi financijskog sektora. Implementirana su dva algoritma trgovanja čiji su rezultati zabilježeni, evaluirani i uspoređeni. Prvi algoritam temelji se na strategiji "presjeka dviju srednjih vrijednosti" (engl. Moving Average Crossover ili MAC), a drugi na "reverziji srednje vrijednosti" (engl. Mean Reversion ili MR). Statističke metode koje je koristio prvi algoritam su: eksponencijalna srednja vrijednost (engl. Exponential Moving Average), srednja vrijednost i prosječni pravi raspon (engl. Average True Range ili ATR). Drugi algoritam koristio je Bollinger Bands, relativni indeks snage (Relative Strength RSI), parabolički stop i obrat (parabolic Stop And Reverse ili SAR) i ATR.
Algoritmi su testirani na glavnim parovima na Forex-u: EURUSD, GBPUSD, USDCHF i USDJPY.
Testirani su na zadnjih dvanaest godina. Forex platforma na kojoj su testirani je MT4.
Broker na kojem je napravljen Demo račun u svrhu rada je Fusion Markets. Algoritam MAC
je u prosjeku ostvario pozitivan povrat, dok je MR ostvario negativan povrat.

Abstract (english)

The goal of this final paper was to program an automated trading strategy that trades with financial instruments based on time series analysis. Time series were analyzed by statistical methods or technical indicators. Algorithmic trading strategies were studied and described, as well as statistical methods on which an estimate of the price movement of the financial instrument is based. Also, the basic principles of the financial sector were elaborated. Two trading algorithms were implemented whose results were plotted, evaluated and compared. The first algorithm was based on the "Moving Average Crossover" or MAC strategy whilst
other one was based on "Mean Reversion" or MR. The statistical methods used by the first algorithm were: Exponential Moving Average, Simple Moving Average and Average True Range (ATR). The second algorithm used Bollinger Bands, Relative Strength Index RSI, Parabolic Stop And Reverse (SAR) and ATR. The algorithms were tested on the major Forex pairs: EURUSD, GBPUSD, USDCHF and USDJPY. They were tested in the period of last twelve years. The forex platform on which they were tested is MT4. The broker on which the Demo account was created for the purpose of this work is Fusion Markets. MAC algorithm achieved a positive return on average, while MR achieved a negative return.

• Keywords: algoritamsko trgovanje; financijska analiza; analiza vremenskih serija; algoritmi; automatizacija; MQL4; Forex; trgovanje
• Keywords (english): algorithmic trading; financial analysis; time series analysis; algorithms; automation; MQL4; Forex; trading
• Language: croatian
• URN:NBN: urn:nbn:hr:168:897946
• 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: 2023-01-15 11:18:39