Statistical/RBF NN framework for high frequency financial data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F21%3A10249575" target="_blank" >RIV/61989100:27510/21:10249575 - isvavai.cz</a>

Výsledek na webu

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

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Statistical/RBF NN framework for high frequency financial data

Popis výsledku v původním jazyce

In this paper, we develop and consider the accuracy of forecasting models based on statistical (stochastic) methods and two intelligent methodology based on SVM approach and neural networks by using novel activation function based on the cloud concept with parameters chosen by a grid search. The use of both intelligent methods is useful because there is no knowledge about the relationship between the inputs into the system and its output. The proposed approaches are applied to predict the high frequency time series of the daily EUR/USD exchange rate time series and assess their prediction performance. We showed that intelligent learning methods have more accurate outputs than the statistical one. On the other hand, the statistical GARCH-class models can identify the presence of the leverage effect and to react to the good and bad news. (C) Proceedings of the 14th International Conference on Strategic Management and its Support by Information Systems 2021, SMSIS 2021.

Název v anglickém jazyce

Statistical/RBF NN framework for high frequency financial data

Popis výsledku anglicky

In this paper, we develop and consider the accuracy of forecasting models based on statistical (stochastic) methods and two intelligent methodology based on SVM approach and neural networks by using novel activation function based on the cloud concept with parameters chosen by a grid search. The use of both intelligent methods is useful because there is no knowledge about the relationship between the inputs into the system and its output. The proposed approaches are applied to predict the high frequency time series of the daily EUR/USD exchange rate time series and assess their prediction performance. We showed that intelligent learning methods have more accurate outputs than the statistical one. On the other hand, the statistical GARCH-class models can identify the presence of the leverage effect and to react to the good and bad news. (C) Proceedings of the 14th International Conference on Strategic Management and its Support by Information Systems 2021, SMSIS 2021.

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 14th International Conference Strategic Management and its Support by Information Systems 2021: May 25-26, 2021, Ostrava, Czech Republic

ISBN

978-80-248-4521-0

ISSN

2570-5776

e-ISSN

—

Počet stran výsledku

10

Strana od-do

178-187

Název nakladatele

VŠB - Technical University of Ostrava

Místo vydání

Ostrava

Místo konání akce

Ostrava

Datum konání akce

25. 5. 2021

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—