Show simple item record

dc.contributor.advisorPerdahçı, Nazım Ziyaen_US
dc.contributor.authorGörgün, Onuren_US
dc.contributor.otherIşık Üniversitesi, Fen Bilimleri Enstitüsü, Enformasyon Teknolojileri Yüksek Lisans Programıen_US
dc.date.accessioned2016-06-03T12:48:00Z
dc.date.available2016-06-03T12:48:00Z
dc.date.issued2008-09-18
dc.identifier.citationGörgün, O. (2008). Neural networks as a forecasting tool for financial decision-making. İstanbul: Işık Üniversitesi Fen Bilimleri Enstitüsü.en_US
dc.identifier.urihttps://hdl.handle.net/11729/931
dc.descriptionText in English ; Abstract: English and Turkishen_US
dc.descriptionIncludes bibliographical references (leaves 40-42)en_US
dc.descriptionix, 42 leavesen_US
dc.description.abstractFor the last decade, machine learning techniques have been applied to financial tasks such as portfolio management, risk assessment and stock market prediction. Among these techniques artificial neural network as a machine learning algorithm is the most widely used model. In stock market environment, multi layer perceptron with backpropagation model is dominant among others in stock market prediction. This study examines the forecasting power of multi layer perceptron models for predicting the direction of ISE 100 daily index value. The results show that multi layer perceptron has a promising power in predicting the stock market trend. However, it also shows that selection of input variables is dominant factor in stock market prediction to obtain accurate results.en_US
dc.description.abstractSon on yılda makine öğrenimi yöntemleri portföy yönetimi, risk değerlendirmesi ve hisse senedi piyasası öngörme gibi finansal problemleri çözmede kullanılmaktadır. Bütün modeller içerisinde yapay sinir ağı ise en fazla uygulanan yöntem olarak görülmektedir. Hisse senedi piyasalarında hata geri yayma yöntemi ile eğitilmis çok katmanlı algılayıcı baskın yapay sinir ağları modelidir. Bu çalışma çok katmanlı algılayıcıların İstanbul Menkul Kıymetler Borsası 100 endeksinin yönünün tahmininde ki gücünü incelemektedir. Sonuçlar çok katmanlı algılayıcının borsa piyasası tahmini konusunda gelecek vadeden bir yapı oldugunu ortaya koymaktadır. Ancak, doğru girdi değişkeni seçiminin isabetli tahmin yapma konusunda ne kadar etkili olduğu da vurgulanmaktadır.en_US
dc.description.tableofcontentsNeural Networks in Financial Tasksen_US
dc.description.tableofcontentsPrediction of Stock Marketen_US
dc.description.tableofcontentsMachine Learningen_US
dc.description.tableofcontentsWhat is Artificial Neural Networken_US
dc.description.tableofcontentsArtificial Neuronen_US
dc.description.tableofcontentsIssues in Artificial Neural Network Modeling for Forecastingen_US
dc.description.tableofcontentsData Specific Issuesen_US
dc.description.tableofcontentsSelection of Input Variablesen_US
dc.description.tableofcontentsData Preprocessingen_US
dc.description.tableofcontentsSensitivity Analysisen_US
dc.description.tableofcontentsTraining, Validation and Test Samplesen_US
dc.description.tableofcontentsNeural Network Architecture Specific Issuesen_US
dc.description.tableofcontentsNetwork Architectureen_US
dc.description.tableofcontentsNumber of Nodes in Each Layeren_US
dc.description.tableofcontentsActivation Functionen_US
dc.description.tableofcontentsTraining Algorithmen_US
dc.description.tableofcontentsPerformance Measuresen_US
dc.description.tableofcontentsPerformance Validation Issuesen_US
dc.description.tableofcontentsPredicting ISE100 Index With Neural Networksen_US
dc.description.tableofcontentsStock Market Applications of ANNs in Turkeyen_US
dc.description.tableofcontentsData Seten_US
dc.description.tableofcontentsNetwork Structureen_US
dc.description.tableofcontentsEmpirical Findingsen_US
dc.language.isoengen_US
dc.publisherIşık Üniversitesien_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subject.lccHG4012.5 .G67 2008
dc.subject.lcshFinance -- Decision making -- Data processing.en_US
dc.subject.lcshNeural networks (Computer science)en_US
dc.subject.lcshComputer science.en_US
dc.titleNeural network as a forecasting tool for financial decision-makingen_US
dc.title.alternativeFinansal karar almada öngörü aracı olarak sinir ağıen_US
dc.typemasterThesisen_US
dc.contributor.departmentIşık Üniversitesi, Fen Bilimleri Enstitüsü, Enformasyon Teknolojileri Yüksek Lisans Programıen_US
dc.contributor.authorID0000-0001-7754-2033
dc.relation.publicationcategoryTezen_US
dc.contributor.institutionauthorGörgün, Onuren_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

info:eu-repo/semantics/openAccess
Except where otherwise noted, this item's license is described as info:eu-repo/semantics/openAccess