A Method of Stock Price Forecasting Based on Recurrent Neural Network
DOI:
https://doi.org/10.54097/7fgvcv74Keywords:
Deep Learning, Stock Forecasting, RNN Neural NetworksAbstract
It is selected the stock data of Kweichow Moutai for a certain period of time, uses python to model and analyze and predict the stock price, compares the predicted stock price with the real stock price, and then uses root mean square error, mean square error, and mean absolute error to evaluate the prediction model. RNN neural network can make good use of the nonlinear stock data and can memorize the effective information in the sequence data. Numerical experiments show that RNN neural network is a desirable stock forecasting method.
Downloads
References
[1] Liu Changkun. Research on stock prediction based on deep learning [D]. Beijing University of Technology. 2018.
[2] Wang Litong, Xue Tengteng, Wang Huimin, Liu Zhen. Research on Stock Index Price Forecasting Based on Recurrent Neural Network [J]. Journal of Zhejiang University of Technology, 2019, 47 (02): 186-191.
[3] Huang Liming, Chen Weizheng, Yan Hongfei, Chen Chong. Stock Forecasting Method Based on Recurrent Neural Network and Deep Learning [J]. Journal of Guangxi Normal University (Natural Science Edition), 2019, 37 (01): 13-22.
[4] Wang Ziyue. Recurrent Neural Network Stock Forecasting [J]. Computer Knowledge and Technology, 2018, 14 (22): 171-172.
[5] Wang Jingwen. Empirical Analysis of Stock Prices Based on Recurrent Neural Network [D]. Yunnan University. 2020.01 .
[6] Yuan Ruyi. Stock Forecast Analysis Based on Deep Learning [J]. China Collective Economy, 2021, (24): 105-106.
[7] Gary Orudnitski & Larry Osburn.Forecasting S&P arid Gold Futures Prices: An Application of Neural Networks Iii. [J]. The Journal of Futures Markets, 1993, 6 (3): 631-643.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Journal of Computer Science and Artificial Intelligence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
