Authors: Radojičić, Dragana 
Radojičić, Nina
Kredatus, Simeon
Title: A multicriteria optimization approach for the stock market feature selection
Journal: Computer Science and Information Systems
Volume: 18
Issue: 3
First page: 749
Last page: 769
Issue Date: 2021
Rank: M23
ISSN: 1820-0214
DOI: 10.2298/CSIS200326044R
This paper studies the informativeness of features extracted from a limit order book data, to classify market data vector into the label (buy/idle) by using the Long short-term memory (LSTM) network. New technical indicators based on the support/resistance zones are introduced to enrich the set of features. We evaluate whether the performance of the LSTM network model is improved when we select features with respect to the newly proposed methods. Moreover, we employ multicriteria optimization to perform adequate feature selection among the proposed approaches, with respect to precision, recall, and Fβ score. Seven variations of approaches to select features are proposed and the best is selected by incorporation of multicriteria optimization.
Keywords: Limit order book | multicriteria optimization | time-series | feature selection | machine learning
Publisher: ComSIS Consortium

Show full item record


checked on Jul 19, 2024

Page view(s)

checked on May 9, 2024

Google ScholarTM




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