Přístupnostní navigace
E-application
Search Search Close
Publication detail
VARYŠOVÁ, T.
Original Title
Time Series Forecasting Using Artificial Neural Network
Type
conference paper
Language
English
Original Abstract
The paper aims to verify the ability of artificial neural networks to model and predict time series with seasonal and trend pattern. In this study the effectiveness of data preprocessing and time series analysis is examined, especially deseasonalization and detrending as a basis for further neural network modelling and forecasting. In this paper it is proved that using deseasonalization as data preprocessing method, the best neural network performance is reached with respect to smallest Mean Squared Error showing the difference between outputs and targets. In general the research shows that prior data preprocessing enhances preciseness of further neural network prediction.
Keywords
Time series; seasonal and trend decomposition; forecasting; neural network
Authors
RIV year
2015
Released
7. 5. 2015
Publisher
International Business Information Management Association (IBIMA)
Location
Amsterdam
ISBN
978-0-9860419-4-5
Book
Proceedings of the 25th International Business Information Management Association Conference
Pages from
527
Pages to
535
Pages count
9
BibTex
@inproceedings{BUT115320, author="Tereza {Šustrová}", title="Time Series Forecasting Using Artificial Neural Network", booktitle="Proceedings of the 25th International Business Information Management Association Conference", year="2015", pages="527--535", publisher="International Business Information Management Association (IBIMA)", address="Amsterdam", isbn="978-0-9860419-4-5" }