Rodyti trumpą aprašą

dc.rights.licenseKūrybinių bendrijų licencija / Creative Commons licenceen_US
dc.contributor.authorMaknickienė, Nijolė
dc.contributor.authorKekytė, Ieva
dc.contributor.authorMaknickas, Algirdas
dc.date.accessioned2024-05-13T07:57:15Z
dc.date.available2024-05-13T07:57:15Z
dc.date.issued2018
dc.identifier.isbn9786094761195en_US
dc.identifier.issn2029-4441en_US
dc.identifier.urihttps://etalpykla.vilniustech.lt/handle/123456789/154209
dc.description.abstractSuccessful trading in financial markets is not possible without a support system that manages the preparation of the data, prediction system, and risk management and evaluates the trading efficiency. Selected orthogonal data was used to predict exchange rates by applying recurrent neural network (RNN) software based on the open source framework Keras and the graphical processing unit (GPU) NVIDIA GTX1070 to accelerate RNN learning. The newly developed software on the GPU predicted ten high-low distributions in approximately 90 minutes. This paper compares different daily algorithmic trading strategies based on four methods of portfolio creation: split equally, optimisation, orthogonality, and maximal expectations. Each investigated portfolio has opportunities and limitations dependent on market state and behaviour of investors, and the efficiencies of the trading support systems for investors in foreign exchange market were tested in a demo FOREX market in real time and compared with similar results obtained for risk-free rates.en_US
dc.format.extent9 p.en_US
dc.format.mediumTekstas / Texten_US
dc.language.isoenen_US
dc.relation.urihttps://etalpykla.vilniustech.lt/handle/123456789/154008en_US
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.source.urihttps://bm.vgtu.lt/index.php/verslas/2018/paper/view/474en_US
dc.subjectcomputation intelligenceen_US
dc.subjectportfolioen_US
dc.subjectfinancial marketsen_US
dc.subjectinvestment decisionen_US
dc.subjectalgorithmic tradingen_US
dc.titleComputation intelligence based daily algorithmic strategies for trading in the foreign exchange marketen_US
dc.typeKonferencijos publikacija / Conference paperen_US
dcterms.accessRightsLaisvai prieinamas / Openly availableen_US
dcterms.accrualMethodRankinis pateikimas / Manual submissionen_US
dcterms.alternativeFinancial engineeringen_US
dcterms.issued2018-05-04
dcterms.licenseCC BYen_US
dcterms.references45en_US
dc.description.versionTaip / Yesen_US
dc.contributor.institutionVilniaus Gedimino technikos universitetasen_US
dc.contributor.institutionVilnius Gediminas Technical Universityen_US
dc.contributor.facultyMechanikos fakultetas / Faculty of Mechanicsen_US
dc.contributor.facultyVerslo vadybos fakultetas / Faculty of Business Managementen_US
dc.contributor.departmentFinansų inžinerijos katedra / Department of Financial Engineeringen_US
dc.contributor.laboratorySkaitinio modeliavimo laboratorija / Laboratory of Numerical Simulationen_US
dcterms.sourcetitle10th International Scientific Conference “Business and Management 2018”en_US
dc.identifier.eisbn9786094761188en_US
dc.identifier.eissn2029-929Xen_US
dc.publisher.nameVilnius Gediminas Technical Universityen_US
dc.publisher.nameVilniaus Gedimino technikos universitetasen_US
dc.publisher.countryLithuaniaen_US
dc.publisher.countryLietuvaen_US
dc.publisher.cityVilniusen_US
dc.identifier.doihttps://doi.org/10.3846/bm.2018.53en_US


Šio įrašo failai

Thumbnail
Thumbnail

Šis įrašas yra šioje (-se) kolekcijoje (-ose)

Rodyti trumpą aprašą

Kūrybinių bendrijų licencija / Creative Commons licence
Išskyrus atvejus, kai nurodyta kitaip, šio įrašo licencija apibrėžiama taipKūrybinių bendrijų licencija / Creative Commons licence