Considering seasonal fluctuations in equalizing time series by
means of artificial neural networks for predicting development
of USA and People ́s Republic of China trade balance

J 2019

Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance

VRBKA, Jaromír, Petr ŠULEŘ, Veronika MACHOVÁ and Jakub HORÁK

Basic information

Original name

Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance

Name in Czech

Zohlednění sezónních výkyvů ve vyrovnávání časových řad pomocí umělých neuronových sítí pro předpovídání vývoje obchodní bilance USA a Čínské lidové republiky

Authors

VRBKA, Jaromír, Petr ŠULEŘ, Veronika MACHOVÁ and Jakub HORÁK

Edition

Littera Scripta, České Budějovice, The Institute of Technology and Business in České Budějovice, 2019, 1805-9112

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

50200 5.2 Economics and Business

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

Organization unit

Institute of Technology and Business in České Budějovice

DOI

http://dx.doi.org/10.36708/Littera_Scripta2019/2/0

Keywords (in Czech)

časové řady; umělé neuronové sítě; obchodní bilance; sezónní výkyvy; další kategoriální proměnná; predikce

Keywords in English

time series; artificial neural networks; trade balance; seasonal fluctuations; additional categorical variable; prediction

Abstract

ORIG CZ

V originále

The aim of the contribution is to propose a methodology for taking into account the seasonal fluctuations in equalizing time series by means of artificial neural networks on the example of the USA and People´s Republic of China trade balance. Regression by means of neural structures is carried out in two alternatives, where the second calculation takes into account the monthly seasonality of the time series. The result indicates that the additional variable in the form of the month in which the value was measured enables more order and accuracy.

In Czech

Cílem tohoto příspěvku je proto navrhnout metodiku zohlednění sezónních výkyvů při vyrovnání časových řad pomocí umělých neuronových sítí na příkladu obchodní bilance USA a Čínské lidové republiky. Provedena je regrese pomocí neuronových struktur, a to ve dvou rozměrech, kdy druhý výpočet bere v úvahu měsíční sezónnost časové řady. Výsledek naznačuje, že dodatečná proměnná v podobě měsíce měření hodnoty vnáší do vyrovnání časových řad větší řád a přesnost.

Files attached

Request the author's version of the file

Citovat

VRBKA, Jaromír, Petr ŠULEŘ, Veronika MACHOVÁ and Jakub HORÁK. Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance. Littera Scripta. České Budějovice: The Institute of Technology and Business in České Budějovice, 2019, vol. 12, No 2, p. 178-193. ISSN 1805-9112. Available from: https://dx.doi.org/10.36708/Littera_Scripta2019/2/0.

@article{52001,
   author = {Vrbka, Jaromír and Šuleř, Petr and Machová, Veronika and Horák, Jakub},
   article_location = {České Budějovice},
   article_number = {2},
   doi = {http://dx.doi.org/10.36708/Littera_Scripta2019/2/0},
   keywords = {time series; artificial neural networks; trade balance; seasonal fluctuations; additional categorical variable; prediction},
   language = {eng},
   issn = {1805-9112},
   journal = {Littera Scripta},
   title = {Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance},
   volume = {12},
   year = {2019}
}

TY  - JOUR
ID  - 52001
AU  - Vrbka, Jaromír - Šuleř, Petr - Machová, Veronika - Horák, Jakub
PY  - 2019
TI  - Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance
JF  - Littera Scripta
VL  - 12
IS  - 2
SP  - 178-193
EP  - 178-193
PB  - The Institute of Technology and Business in České Budějovice
SN  - 18059112
KW  - time series
KW  - artificial neural networks
KW  - trade balance
KW  - seasonal fluctuations
KW  - additional categorical variable
KW  - prediction
N2  - The aim of the contribution is to propose a methodology for taking into account the seasonal fluctuations in equalizing time series by means of artificial neural networks on the example of the USA and People´s Republic of China trade balance. Regression by means of neural structures is carried out in two alternatives, where the second calculation takes into account the monthly seasonality of the time series. The result indicates that the additional variable in the form of the month in which the value was measured enables more order and accuracy.
ER  -

VRBKA, Jaromír, Petr ŠULEŘ, Veronika MACHOVÁ and Jakub HORÁK. Considering seasonal fluctuations in equalizing time series by means of artificial neural networks for predicting development of USA and People ́s Republic of China trade balance. \textit{Littera Scripta}. České Budějovice: The Institute of Technology and Business in České Budějovice, 2019, vol.~12, No~2, p.~178-193. ISSN~1805-9112. Available from: https://dx.doi.org/10.36708/Littera\_{}Scripta2019/2/0.

Detailed Information on Publication Record