Research Article
Survey on Stock Prediction Based on Deep Learning
@INPROCEEDINGS{10.4108/eai.29-3-2024.2347394, author={Guoxing Guo and Hongmin Wang}, title={Survey on Stock Prediction Based on Deep Learning}, proceedings={Proceedings of the 3rd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2024, March 29--31, 2024, Wuhan, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2024}, month={6}, keywords={stock forecast; neural network; deep learning; machine learning}, doi={10.4108/eai.29-3-2024.2347394} }
- Guoxing Guo
Hongmin Wang
Year: 2024
Survey on Stock Prediction Based on Deep Learning
ICBBEM
EAI
DOI: 10.4108/eai.29-3-2024.2347394
Abstract
Stock prediction has always been a hot topic in the field of research. In the present era,along with the Internet rapid development,all kinds of complicated information are easy to affect the accuracy of people's judgment. Therefore, how to establish a stock prediction model with both accuracy and computing speed is of great importance to investors. Researchers are committed to the exploration of the stock market, looking for the development law of the market for stocks, in order to realize the purpose of grasping the law of the equity market in advance. This paper conducted a comprehensive study on various stock prediction models, introduced the time series based model, long short-term memory network model, convolutional neural network model, radial basis network model, back propagation neural network model, support vector machine model and combination model, and introduced the advantages and disadvantages of each model. It also makes a comprehensive summary and outlook on the stock forecasting methods, and provides an accurate and powerful judgment for the majority of investors.