prikaz prve stranice dokumenta Razvoj momentnih strategija metodom slučajnih šuma
No public access
master's thesis
Razvoj momentnih strategija metodom slučajnih šuma
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. urn:nbn:hr:168:740882
Pavlić, Paula
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pavlić, P. (2015). Razvoj momentnih strategija metodom slučajnih šuma (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:740882

Pavlić, Paula. "Razvoj momentnih strategija metodom slučajnih šuma." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:740882

Pavlić, Paula. "Razvoj momentnih strategija metodom slučajnih šuma." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2015. https://urn.nsk.hr/urn:nbn:hr:168:740882

Pavlić, P. (2015). 'Razvoj momentnih strategija metodom slučajnih šuma', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:740882

Pavlić P. Razvoj momentnih strategija metodom slučajnih šuma [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2015 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:740882

P. Pavlić, "Razvoj momentnih strategija metodom slučajnih šuma", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:168:740882

Metadata
TitleRazvoj momentnih strategija metodom slučajnih šuma
Title (english)Random forest method for momentum strategies
AuthorPaula Pavlić
MentorZvonko Kostanjčar (mentor)
Committee memberZvonko Kostanjčar (predsjednik povjerenstva)
Committee memberDražen Jurišić (član povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2015-02-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Unutar ovog rada prikazana je mogućnost upotrebe strojnog učenja u financijskim strategijama temeljenim na momentu, točnije upotreba slučajnih šuma na tržištu dionica. Konstruiran je model koji koristi karakteristike dionica kao atribute za izgradnju slučajne šume, te na temelju naučene veze između tih atributa i stvarnih klasa podataka iz seta za treniranje vrši predikciju i za svaki novi dan daje moguću klasu prema kojoj se ostvaruje investicijska strategija. Algoritam je implementiran unutar programskog sustava MATLAB, a korištena je metoda ojačanih šuma kako bi se potencirali oni rezultati koji daju najbolju zaradu koja je osnovni cilj svake financijske strategije. Analiza je provedena nad 10, a prikazani su rezultati za 5 dionica sa Zagrebačke burze.
Abstract (english)
In this thesis it is shown how it is possible to use methods of machine learning in financial strategies based on momentum, or more specifically, how to use random forest algorithm when trading shares. A model that uses characteristics of each share as attributes to build random forests is built to predict possible classes of share prices which are used to execute an investment strategy, using links between true classes of the training set data and the attributes that the algorithm has learnt by itself. The algorithm is implemented inside MATLAB, and it uses the reinforced method to potentiate results that give the best possible earnings, which is the goal of every investment strategy. The analysis is run on 10 and results are shown for 5 shares from the Zagreb stock exchange.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:740882
Study programmeTitle: Information and Communication Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 23:42:26