Research on Multi-factor Stock Selection Strategy based on Improved Particle Swarm Support Vector Machine

DOI

10.2991/edmi-19.2019.72How to use a DOI?

Keywords

SVM algorithm, nearest neighbor method, improved discrete particle swarm optimization.

Abstract

In recent years, the application of machine learning in quantitative trading has attracted more and more attention. In this paper, a new support vector machine algorithm based on nearest neighbor method and improved discrete particle swarm optimization is proposed. Taking Hu-Shen 300 stocks as the research object, the improved support vector machine and the original support vector machine are used to construct multi-factor stock selection strategies respectively, and the two strategies are compared in the back-test analysis. The results show that the multi-factor stock selection strategy of support vector machine based on nearest neighbor method and improved discrete particle swarm optimization has higher annual return than the original SVM algorithm, and has good execution effect.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Canran Xiao
AU  - Liwei Hou
AU  - Jun Huang
PY  - 2019/08
DA  - 2019/08
TI  - Research on Multi-factor Stock Selection Strategy based on Improved Particle Swarm Support Vector Machine
BT  - Proceedings of the 1st International Symposium on Economic Development and Management Innovation (EDMI 2019)
PB  - Atlantis Press
SP  - 437
EP  - 441
SN  - 2352-5428
UR  - https://doi.org/10.2991/edmi-19.2019.72
DO  - 10.2991/edmi-19.2019.72
ID  - Xiao2019/08
ER  -