Prediction of high stock transfer of listed companies based on deep learning

Qitan Lv; Tengjin Chen; Haichao Yao

doi:10.1117/12.2641290

4 August 2022 Prediction of high stock transfer of listed companies based on deep learning

Qitan Lv, Tengjin Chen, Haichao Yao

Proceedings Volume 12306, Second International Conference on Digital Signal and Computer Communications (DSCC 2022); 123061H (2022) https://doi.org/10.1117/12.2641290
Event: Second International Conference on Digital Signal and Computer Communications (DSCC 2022), 2022, Changchun, China

Abstract

Recently, the high-payment transfer of Chinese A-shares in stock investment has been highly sought after by small and medium-sized investors and has gradually become a spotlight. Listed companies make ex-rights treatment of their stocks when making high-send and transfer decisions. Investors who buy at this stage can make profits through stock appreciation in a short period. Many companies will immediately increase the daily limit when trading at a high price. Therefore, predicting the decision and buying in advance is of significance to investors. This paper uses the income statement and "high delivery" data of the vaccine cold chain, battery, steel, and planting and forestry sectors from 2010 to 2021 ,using Random Forest and XGBoost to screen out six high contributions factors with significant influence. We also use mean values to fill indicators with a missing ratio below 30% and remove the mean value of high delivery data. Then we establish a prediction model based on different Neural Network models. Some networks show high performance, in which the CNN network with regularization methods, weight decay, and dropout is the best, reaching 93 % of accuracy.

Citation Download Citation

Qitan Lv, Tengjin Chen, and Haichao Yao "Prediction of high stock transfer of listed companies based on deep learning", Proc. SPIE 12306, Second International Conference on Digital Signal and Computer Communications (DSCC 2022), 123061H (4 August 2022); https://doi.org/10.1117/12.2641290

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available