Primjena optimizacijskih metoda u razvoju investicijskih strategija

undergraduate thesis

• Title (english): Investment strategies development using optimization methods
• Author: Luka Manola
• Mentor: Zvonko Kostanjčar (mentor)
• Committee member: Zvonko Kostanjčar (predsjednik povjerenstva)
• Committee member: Dražen Jurišić (član povjerenstva)
• Committee member: Ana Sović Kržić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom završnom radu ispitana je primjenjivost optimizacijskih postupaka u razvoju investicijskih strategija. Analiza je provedena na četrnaest najlikvidnijih dionica sa Zagrebačke burze. Za svaku je dionicu iz povijesnih podataka konstruiran vektor značajki koji je potom pomoću funkcije cilja preslikan u prostor realnih brojeva. Vektor značajki i funkcija cilja temelje se na indikatorima tehničke analize. Provedeni optimizacijski postupak baziran je na algoritmu slučajnih šuma i metodi regresije. Model je testiran na podacima koji nisu korišteni u optimizacijskom postupku. Pokazana je prednost dinamičke strategije za kreiranje portfelja pred burzovnim indeksom te strategijom diverzifikacije portfelja.

Abstract (english)

In this thesis we examine the applicability of optimization methods in the development of investment strategies. The analysis was conducted on fourteen most liquid stocks on the Zagreb Stock Exchange. For every stock, feature vector was designed from historical data, which was then mapped in the real numbers space, using the objective function. Feature vector and objective function stem from the technical analysis indicators. Implemented optimization method is based on the random forest algorithm for regression. The model was tested on data that were not used during the optimization procedure. The advantage of dynamic portfolio creation strategy has been shown when compared to stock indices and portfolio diversification strategy.

• Keywords: optimizacija portfelja; financijska tržišta; investicijska strategija; algoritam slučajnih šuma; vektor značajki
• Keywords (english): portfolio optimization; financial markets; investment strategy; random forest algorithm; feature vector
• Language: croatian
• URN:NBN: urn:nbn:hr:168:981091
• 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: 2018-02-05 17:42:48