VGTU talpykla > Verslo vadybos fakultetas / Faculty of Business Management > Moksliniai straipsniai / Research articles >

Lietuvių   English
Please use this identifier to cite or link to this item: http://dspace.vgtu.lt/handle/1/3568

Title: High-low Strategy of Portfolio Composition using Evolino RNN Ensembles
Authors: Stankevičienė, Jelena
Maknickienė, Nijolė
Maknickas, Algirdas
Keywords: Finance Markets
Evolino
High-Low Strategy
Investment Portfolio
Prediction
Issue Date: 2017
Publisher: KTU
Citation: Stankevičienė, J.; Maknickienė, N.; Maknickas; A. 2017. High-low Strategy of Portfolio Composition using Evolino RNN Ensembles, Inžinerinė Ekonomika-Engineering Economics 28(2): 162–169
Series/Report no.: 28;2
Abstract: Strategy of investment is important tool enabling better investor’s decisions in uncertain finance market. Rules of portfolio selection help investors balance accepting some risk for the expectation of higher returns. The aim of the research is to propose strategy of constructing investment portfolios based on the composition of distributions obtained by using high–low data. The ensemble of 176 Evolino recurrent neural networks (RNN) trained in parallel investigated as an artificial intelligence solution, which applied in forecasting of financial markets. Predictions made by this tool twice a day with different historical data give two distributions of expected values, which reflect future dynamic exchange rates. Constructing the portfolio, according to the shape, parameters of distribution and the current value of the exchange rate allows the optimization of trading in daily exchange-rate fluctuations. Comparison of a high-low portfolio with a close-to-close portfolio shows the efficiency of the new forecasting tool and new proposed trading strategy.
URI: http://dspace.vgtu.lt/handle/1/3568
ISSN: 1392-2785
Appears in Collections:Moksliniai straipsniai / Research articles

Files in This Item:

File Description SizeFormat
High-low strategy of portfolio composition using Evolino RNN ensembles.pdf692.54 kBAdobe PDFView/Open

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

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback