Naslov
The importance of time series data filtering for predicting the direction of stock market movement using neural networks

Autori
Botunac, Ive ; Panjkota, Ante ; Matetić, Maja

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 30th International DAAAM Symposium ''Intelligent Manufacturing & Automation'' / - , 2019, 886-891

ISBN
978-3-902734-22-8

Skup
30th DAAAM International Symposium on Intelligent Manufacturing and Automation

Mjesto i datum
Zadar, Hrvatska, 20.10.2019. - 27.10.2019

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
stock market prediction ; machine learning ; neural network ; wavelet transformation

Sažetak
Predicting future trends in the stock market from time-series data is a challenging task due to its high non-linear nature caused by the complexity involved in the trading process. This paper emphasizes the importance of time- series dana filtering when neural network models are used for stock market direction forecasting. Performances of three different neural network models are compared on raw data, processed data with simple moving average, and data filtered with discrete wavelet transformation. Applying wavelet transformation on input financial data as a processing step shows better results than the use ofraw financial data or simple moving average. Also, among tested neural network models, the better results are obtained by using long short-term neural network then by using other neural network models.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Ekonomija, Informacijske i komunikacijske znanosti

POVEZANOST RADA