DC FieldValueLanguage
dc.contributor.authorRadojičić, Draganaen_US
dc.contributor.authorKredatus, Simeonen_US
dc.date.accessioned2020-12-09T10:34:39Z-
dc.date.available2020-12-09T10:34:39Z-
dc.date.issued2020-11-30-
dc.identifier.issn0957-4174-
dc.identifier.urihttp://researchrepository.mi.sanu.ac.rs/handle/123456789/4284-
dc.description.abstractIn this paper, we suggest new feature extraction models based on the stock market price signal analysis. In particular, we study the behavior observed in signals originating from different sources, such as prices of different Limit Order Book levels and open, close, low, high prices of the preselected time intervals. We apply Fourier transformation to extract new features. Moreover, we evaluate if the performance of the model based on the Gated Recurrent Unit (GRU) architecture is improved when we select features utilizing the proposed methods. Furthermore, we benchmark the performance of new indicators on the GRU model and provide quantified results proving the significant performance improvement obtained by incorporating the suggested features.en_US
dc.publisherElsevieren_US
dc.relation.ispartofExpert Systems with Applicationsen_US
dc.subjectFourier transform | Limit Order Book | Recurrent Neural Networks | Technical indicatorsen_US
dc.titleThe impact of stock market price Fourier transform analysis on the Gated Recurrent Unit classifier modelen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.eswa.2020.113565-
dc.identifier.scopus2-s2.0-85085771738-
dc.relation.firstpage113565-
dc.relation.volume159-
dc.description.rankM21a-
item.grantfulltextnone-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.openairetypeArticle-
item.fulltextNo Fulltext-
crisitem.author.orcid0000-0001-7850-2623-
Show simple item record

SCOPUSTM   
Citations

20
checked on Dec 12, 2024

Page view(s)

26
checked on Dec 12, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.