Overcoming the Challenges of Uncertainty in Forecasting Economic Time Series Through Convolutional Neural Networks and Other Intelligent Approaches

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F23%3A10253257" target="_blank" >RIV/61989100:27510/23:10253257 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-39777-6_61" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-39777-6_61</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-39777-6_61" target="_blank" >10.1007/978-3-031-39777-6_61</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Overcoming the Challenges of Uncertainty in Forecasting Economic Time Series Through Convolutional Neural Networks and Other Intelligent Approaches

Popis výsledku v původním jazyce

This article provides insights into the use of artificial neural networks (ANNs) and convolutional neural networks (CNNs) as the tools for forecasting economic time series, where uncertainty refers to incomplete information about the future. To improve the forecasting ability of CNN architectures and capture long-term dependencies in the input sequence we used the WaveNet models which dilate convolutions with skip connections in the input sequence. The residual blocks with skip connections are defined in a specific way that allows for easier information flow through the network while avoiding the vanishing gradient problem, making it a potential innovation in the field of deep learning. Another innovative aspect is the use one-hot encoding for the target sequences using categorical cross-entropy loss function.

Název v anglickém jazyce

Overcoming the Challenges of Uncertainty in Forecasting Economic Time Series Through Convolutional Neural Networks and Other Intelligent Approaches

Popis výsledku anglicky

This article provides insights into the use of artificial neural networks (ANNs) and convolutional neural networks (CNNs) as the tools for forecasting economic time series, where uncertainty refers to incomplete information about the future. To improve the forecasting ability of CNN architectures and capture long-term dependencies in the input sequence we used the WaveNet models which dilate convolutions with skip connections in the input sequence. The residual blocks with skip connections are defined in a specific way that allows for easier information flow through the network while avoiding the vanishing gradient problem, making it a potential innovation in the field of deep learning. Another innovative aspect is the use one-hot encoding for the target sequences using categorical cross-entropy loss function.

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

Lecture Notes in Networks and Systems. Volume 759

ISBN

978-3-031-39776-9

ISSN

2367-3370

e-ISSN

2367-3389

Počet stran výsledku

8

Strana od-do

515-522

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Istanbul

Datum konání akce

22. 8. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—