Research on stock trading prediction based on MAD and Q-learning

Yikai Sun; Ming Gao; Chuyuan Yang; Dong Yuan; Penghui Zhu; Hao Dong; Neng Zhou

doi:10.1117/12.2668175

28 March 2023 Research on stock trading prediction based on MAD and Q-learning

Yikai Sun, Ming Gao, Chuyuan Yang, Dong Yuan, Penghui Zhu, Hao Dong, Neng Zhou

Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 1256649 (2023) https://doi.org/10.1117/12.2668175
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China

Abstract

The accuracy of traditional stock trading prediction is lacking, and stock trading is risky, so this study tries to use machine learning models for stock trading change prediction in big data. This study proposes an algorithm based on the combination of the MAD (Median Absolute Deviation) method and Q-learning model to improve the accuracy of predicting stock trades. The simulation results based on "^GSPC" data show that the new method can better help predict stocks. Of course, this study has some limitations, as the method currently adopts a combination of traditional econometric models and machine learning models, which has some efficiency problems. However, the method proposed in this study is innovative and can provide new ideas for stock price trend prediction and provide new research methods and perspectives for stock market practitioners.

Citation Download Citation

Yikai Sun, Ming Gao, Chuyuan Yang, Dong Yuan, Penghui Zhu, Hao Dong, and Neng Zhou "Research on stock trading prediction based on MAD and Q-learning", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 1256649 (28 March 2023); https://doi.org/10.1117/12.2668175

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