Stock price prediction model based on BP neural network for feature selection

Chaoxiong Lin

doi:10.1117/12.2638720

17 May 2022 Stock price prediction model based on BP neural network for feature selection

Chaoxiong Lin

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122595A (2022) https://doi.org/10.1117/12.2638720
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China

Abstract

Stock price prediction is an important financial research problem. In view of the major defect of large error in stock price prediction based on BP neural network, this paper introduces the improved genetic algorithm (IGA) and BP neural network for feature selection. Establish a mapping relationship between IGA optimization process and BP neural network optimization process, use small-scale IGA and large-scale BP neural network to screen the stock characteristic indicators, so as to reduce the dimension of characteristic data and eliminate irrelevant variables. Finally, the IGA-BPBP model and BP, GA-BP, SOM-BPN, SOM-GA-BP and PCA-IFOA-BP prediction models were used for experimental simulation of the characteristic data of "Ping An Bank" and "Wave Software". MAPE and R^2 were used to evaluate the predictive performance of the model. The simulation results show that the prediction accuracy of IGA-BP-BP model in this paper is higher than that of other models, with each index reduced by 50%~80%, R^2 index increased by 5% on average, and characteristic variables reduced by 48% on average. Therefore, the IGA-BP-BP model in this paper is more efficient.

Citation Download Citation

Chaoxiong Lin "Stock price prediction model based on BP neural network for feature selection", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122595A (17 May 2022); https://doi.org/10.1117/12.2638720

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