A method for representing stock time series features based on trend and inclination angle turning points

Lei Han1 and Xuedong Gao1

  1. School of Economics and Management, University of Science and Technology Beijing
    100083 Beijing,China
    D202210486@xs.ustb.edu.cn, gaoxuedong@manage.ustb.edu.cn

Abstract

Stock time series data mining faces significant challenges in terms of time and space. Time series feature representation is an important means of reducing the dimensionality of time series. This study proposes a stock time series feature representation method based on a combination of slope angle changes and trend turning point screening. This method alleviates the limitations of single methods, such as local feature overfitting, loss of global trends, and sparse long-segment features, through a multi-level collaborative mechanism of screening, filtering, and supplementation. Experimental results show that compared with four other methods, the proposed method effectively preserves the original features of stock time series, achieving good results in both similarity metrics and fitting errors.

Key words

stock time series, feature representation, inclination angle turning point, trend analysis

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS250710074H

Publication information

Volume 23, Issue 1 (January 2026)
Year of Publication: 2026
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Han, L., Gao, X.: A method for representing stock time series features based on trend and inclination angle turning points. Computer Science and Information Systems, Vol. 23, No. 1, 165-184. (2026), https://doi.org/10.2298/CSIS250710074H