Model optimizacije portfelja zasnovan na predviđanju trendova

undergraduate thesis

• Title (english): Portfolio Optimization Model Based on Trend Prediction
• Author: Filip Šimek
• Mentor: Zvonko Kostanjčar (mentor)
• Committee member: Zvonko Kostanjčar (predsjednik povjerenstva)
• Committee member: Tomislav Kovačević (član povjerenstva)
• Committee member: Stjepan Begušić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovome radu naslova Model optimizacije portfelja zasnovan na predviđanju trendova razvili smo dvije metode procjenjivanja budućih očekivanih povrata i implementirali ih u Markowitzev (Mean-Variance) model optimizacije portfelja. Napravili smo usporednu analizu performansi dobivenih efikasnih portfelja pomoću okvira za algoritamsko trgovanje mercury, a korištenjem dvije razvijene metode i treće, široko poznate, metode procjenjivanja povrata preko njihovog prosjeka u prošlosti koja se koristi u Mean Reversion strategiji trgovanja. Naše razvijene metode spadaju pod strategiju trgovanja praćenjem trendova (eng. trend-trading), a indikatori koje koristimo za otkrivanje trendova su l1 i Hodrick-Prescott filtri. Dobiveni rezultati testiranja nam pokazuju kako obje razvijene metode ostvaruju bolje performanse od trećeg korištenog modela (tzv. Mean portfelja) te S&P500 indeksa na promatranom razdoblju od 1990. do 2018. godine

Abstract (english)

In this paper entitled Portfolio Optimization Model Based on Trend Prediction, we have developed two methods for estimating future expected returns and implemented them in Markowitz (Mean-Variance) portfolio optimization model. We made a comparative analysis of the generated efficient portfolios performances using the mercury algorithmic trading framework, using two developed methods and a third, widely known, method of estimating returns over their average in the past used in the Mean Reversion trading strategy. Our developed methods fall under the trend-trading strategy, and the indicators we use to detect trends are l1 and Hodrick-Prescott filters. The obtained test results show us that both developed methods achieve better performances than the third used model (our so-called Mean portfolio) and the S&P500 index in the observed period from 1990. to 2018.

• Keywords: Markowitzev model; l1 filtar; Hodrick-Prescott filtar; diverzifikacija; efikasna granica; praćenje trendova; optimizacija portfelja; strategije trgovanja; algoritamsko trgovanje
• Keywords (english): Markowitz model; l1 filter; Hodrick-Prescott filter; diversification; Efficient Frontier; trend-trading; portfolio optimization; trading strategies; algorithmic trading
• Language: croatian
• URN:NBN: urn:nbn:hr:168:368838
• 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: 2023-01-13 16:16:02