izpis_h1_title_alt

Izbor trgovalnega portfelja z uporabo ansambelskih metod strojnega učenja : magistrsko delo
ID Podlogar, Jure (Author), ID Košir, Tomaž (Mentor) More about this mentor... This link opens in a new window, ID Cergol, Boris (Co-mentor)

.pdfPDF - Presentation file, Download (1,30 MB)
MD5: 0631DC7788D4A625480B1AFC28BCB7BF

Abstract
V tem magistrskem delu je raziskano delovanje ansambelskih metod za izbor trgovalnega portfelja. Algoritmi strojnega učenja se čedalje pogosteje uporabljajo za avtomatizacijo in izboljšanje različnih procesov. Pri uporabi strojnega učenja lahko izbiramo med številnimi različnimi algoritmi, ki pa so za rešitev različnih problemov različno primerni. Izboru neprimernega algoritma se lahko izognemo tako, da uporabimo ansambelske metode stojnega učenja, pri katerih združimo več algoritmov. Poleg predstavitve teoretičnih razlogov za delovanje ansambelskih metod so v tem magistrskem delu izbrane ansambelske metode uporabljene pri implementaciji trgovalne strategije. Trgovalne strategije, ki uporabljajo ansambelske metode, na testni množici podatkov prinašajo znatno višje donose kot primerjalni indeks. Donose povečajo tudi glede na večino algoritmov strojnega učenja, ki so uporabljeni za oblikovanje ansamblov. To nam pokaže, da se lahko s pomočjo ansambelskega učenja vsaj izognemo izboru najmanj primernih algoritmov strojnega učenja za naš problem.

Language:Slovenian
Keywords:strojno učenje, ansambelsko učenje, meta-učenje, izbor portfelja.
Work type:Master's thesis/paper (mb22)
Typology:2.09 - Master's Thesis
Organization:FMF - Faculty of Mathematics and Physics
Year:2018
PID:20.500.12556/RUL-105187 This link opens in a new window
UDC:519.8
COBISS.SI-ID:18476377 This link opens in a new window
Publication date in RUL:08.11.2018
Views:715
Downloads:287
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Portfolio selection using ensemble machine learning
Abstract:
This thesis explores the use of ensemble machine learning algorithms for portfolio selection. Machine learning algorithms are increasingly used to automate and improve processes across a wide range of fields. It is possible to choose between many different algorithms, but not all of them are suitable to solve a given problem. In order to avoid selecting an inappropriate algorithm, ensemble learning methods can be used, as they combine multiple learning algorithms. This thesis starts by presenting theoretical reasons for ensemble learning methods to work. Then, a selection of ensemble learning methods is used in the implementation of a trading strategy. The trading strategies based on ensemble learning methods produce considerably higher returns compared to the benchmark index, when applied to a historical test dataset. In most cases, the returns of such strategies are also higher than those obtained when using the individual algorithms which form part of the ensemble. This shows that ensemble learning methods can help us avoid using the least suitable machine learning algorithms to solve a given problem.

Keywords:machine learning, ansamble learning, meta-learning, portfolio selection.

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back