Prediction Method of Stock Fluctuation Trend Based on LASSO-BPNN

DOI

10.2991/aebmr.k.210319.080How to use a DOI?

Keywords

LASSO-BPNN, prediction method, stock fluctuation trend, China’s A-share market, empirical analysis

Abstract

As an important part of the securities industry, the stock market has always attracted the attention of investors. In view of the fact that there are many factors affecting the stock market and it is difficult to predict, this paper proposes a prediction method of stock fluctuation trend based on LASSO-BPNN. Firstly, the influencing factors of stock fluctuation trend are analyzed, and the variables which have significant influence on stock price are selected by LASSO method. Secondly, on the basis of variable selection, the prediction model of stock fluctuation trend based on LASSO-BPNN is constructed to predict a new energy stock in China’s A-share market. Finally, empirical analysis is carried out to verify the accuracy of the method. The empirical results show that the prediction method proposed in this paper accurate for the stock fluctuation trend judgment, which is suitable for the analysis of stock market. According to the prediction results, some investment suggestions are put forward at the end of this paper.

Copyright

© 2021, 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  - Hongzheng Li
PY  - 2021
DA  - 2021/03/22
TI  - Prediction Method of Stock Fluctuation Trend Based on LASSO-BPNN
BT  - Proceedings of the 6th International Conference on Financial Innovation and Economic Development (ICFIED 2021)
PB  - Atlantis Press
SP  - 439
EP  - 443
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.210319.080
DO  - 10.2991/aebmr.k.210319.080
ID  - Li2021
ER  -