Stock value and currency exchange rate prediction using an artificial neural network trained by a genetic algorithm

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F19%3A10242772" target="_blank" >RIV/61989100:27510/19:10242772 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.ekf.vsb.cz/smsis/en" target="_blank" >https://www.ekf.vsb.cz/smsis/en</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Stock value and currency exchange rate prediction using an artificial neural network trained by a genetic algorithm

Popis výsledku v původním jazyce

Prediction of a stock value or a currency exchange rate is a complex problem which has benefited from recent advancements and research in machine learning. Very popular model for the predictions are deep neural networks. This paper discusses two training algorithms for the feedforward neural networks the backpropagation algorithm and a genetic algorithm. Although the backpropagation algorithm is a reliable way to train a neural network, it can be very demanding on computational resources for lager datasets which are common in some types of trading. Heuristics like the genetic algorithms can help to lower the demands of the training process. The discussed genetic algorithm is an implementation of a classical genetic algorithm with Rank selection of parents for crossover and genes represented as a real number. The accuracy of predictions made by the network trained using this algorithm is then compared to the network trained by backpropagation. (C) 2019 VSB-Technical University of Ostrava. All rights reserved.

Název v anglickém jazyce

Stock value and currency exchange rate prediction using an artificial neural network trained by a genetic algorithm

Popis výsledku anglicky

Prediction of a stock value or a currency exchange rate is a complex problem which has benefited from recent advancements and research in machine learning. Very popular model for the predictions are deep neural networks. This paper discusses two training algorithms for the feedforward neural networks the backpropagation algorithm and a genetic algorithm. Although the backpropagation algorithm is a reliable way to train a neural network, it can be very demanding on computational resources for lager datasets which are common in some types of trading. Heuristics like the genetic algorithms can help to lower the demands of the training process. The discussed genetic algorithm is an implementation of a classical genetic algorithm with Rank selection of parents for crossover and genes represented as a real number. The accuracy of predictions made by the network trained using this algorithm is then compared to the network trained by backpropagation. (C) 2019 VSB-Technical University of Ostrava. All rights reserved.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 13th International Conference on Strategic Management and its Support by Information Systems: May 21th-22th, 2019, Ostrava, Czech Republic

ISBN

978-80-248-4305-6

ISSN

2570-5776

e-ISSN

—

Počet stran výsledku

10

Strana od-do

348-357

Název nakladatele

VŠB - Technical University of Ostrava

Místo vydání

Ostrava

Místo konání akce

Ostrava

Datum konání akce

21. 5. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—