Comparing the performance of deep learning neural network architectures for predicting economic time series

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F23%3A10253148" target="_blank" >RIV/61989100:27510/23:10253148 - 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

Comparing the performance of deep learning neural network architectures for predicting economic time series

Popis výsledku v původním jazyce

We propose two deep learning algorithms for neural network models. The first one the Long short-term memory model and the second one convolutional neural network architecture. These architectures were designed for predicting time series and are evaluated on daily historical stock price data for Apple Inc. The datasets collected from oanda website were used as inputs. Both models were designed according to describing in theoretical background using toolkit of Keras and tested using MSE, RMSE. The achieved prediction accuracy obtained through the proposed deep learning convolutional neural network was much worse than long short-term memory model.

Název v anglickém jazyce

Comparing the performance of deep learning neural network architectures for predicting economic time series

Popis výsledku anglicky

We propose two deep learning algorithms for neural network models. The first one the Long short-term memory model and the second one convolutional neural network architecture. These architectures were designed for predicting time series and are evaluated on daily historical stock price data for Apple Inc. The datasets collected from oanda website were used as inputs. Both models were designed according to describing in theoretical background using toolkit of Keras and tested using MSE, RMSE. The achieved prediction accuracy obtained through the proposed deep learning convolutional neural network was much worse than long short-term memory model.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 15th International Conference on Strategic Management and its Support by Information Systems 2023: May 22-24, 2023, Ostrava, Czech Republic

ISBN

978-80-248-4687-3

ISSN

2570-5776

e-ISSN

—

Počet stran výsledku

8

Strana od-do

192-199

Název nakladatele

VŠB - Technical University of Ostrava

Místo vydání

Ostrava

Místo konání akce

Ostrava

Datum konání akce

22. 5. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—