Authors: Radojičić, Dragana 
Kredatus, Simeon
Title: The impact of stock market price Fourier transform analysis on the Gated Recurrent Unit classifier model
Journal: Expert Systems with Applications
Volume: 159
First page: 113565
Issue Date: 30-Nov-2020
Rank: M21a
ISSN: 0957-4174
DOI: 10.1016/j.eswa.2020.113565
In this paper, we suggest new feature extraction models based on the stock market price signal analysis. In particular, we study the behavior observed in signals originating from different sources, such as prices of different Limit Order Book levels and open, close, low, high prices of the preselected time intervals. We apply Fourier transformation to extract new features. Moreover, we evaluate if the performance of the model based on the Gated Recurrent Unit (GRU) architecture is improved when we select features utilizing the proposed methods. Furthermore, we benchmark the performance of new indicators on the GRU model and provide quantified results proving the significant performance improvement obtained by incorporating the suggested features.
Keywords: Fourier transform | Limit Order Book | Recurrent Neural Networks | Technical indicators
Publisher: Elsevier

Show full item record


checked on Feb 22, 2024

Page view(s)

checked on Feb 22, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.