Research on Stock Price Prediction Based on LSTM Neural Network Modeling

Lingling Zeng; Junhong Li

doi:10.54097/8kp7bf18

Authors

Lingling Zeng
Junhong Li

DOI:

https://doi.org/10.54097/8kp7bf18

Keywords:

Stock Price Prediction; Deep Learning; RNN; LSTM; BiLSTM.

Abstract

The stock market, as a barometer of the national economy, dynamically reacts to the basic situation of economic operation in real time. Stock price prediction has become even more of a problem for investors, and deep learning algorithms are being widely used in financial instrument price prediction, market trend analysis, investment opportunity determination and portfolio optimization, etc. In this paper, the main use of RNN and LSTM neural network models to predict stock price changes, for this purpose, Ping An Bank, selected from January 1, 2015 to June 1, 2024 A total of 2,287 historical data of stock prices are studied, and it is found that the model predicts the price with a better fit to the real price, and comparing the prediction errors of LSTM, CNN-LSTM, and CNN-BiLSTM models, it is found that the BiLSTM model has the smallest error in predicting the stock price, and it possesses higher prediction accuracy.

Downloads

Download data is not yet available.

References

[1] Sharma,Suresh Kumar and Vinod Sharma.“Comparative Analysis of Machine Learning Techniques in Sale Forecasting.” International Journal of Computer Applications 53 (2012): 51-54.

[2] Alsharef A,Sonia,Arora M,et al.Predicting Time-Series Data Using Linear and Deep Learning Models—An Experimental Study[J]. 2022.

[3] Huang J,Wang Y.Comparative Analysis of Different Machine Learning Techniques in Forecasting Stock Price.International Conference on Artificial Intelligence Innovation[J].2024.

[4] Kalidindi A R,Ramisetty N S,Kruthiventi S S,et al.Comparative Analysis of RNN Variants Performance in Stock Price Prediction[J]. 2023.

[5] Liu Weilong,Zhang Yong,Yang Xingyu.Online financing and bond portfolio trading strategy based on LSTM prediction information[J].Systems Engineering Theory and Practice,2024.

[6] Goyal A,Choudhary A,Malik D,et al.Implementing andAnalysis ofRNN LSTM Model forStock Market Prediction[J]. 2023.

[7] Alsharef A,Bhuyan P,Ray A.Predicting Stock Market Prices using Fine-Tuned IndRNN[J].International Journal of Innovative Technology and Exploring Engineering, 2020, 9(7):7.

[8] Zhang Y,Li L.RF-MIP-LSTM stock price prediction model[J]. Computer Engineering and Applications:1-14[2024-06-18].

[9] Xiao Tiantian.Stock price prediction of securities based on K-means-LSTM model[J]. Science and Industry,2024,24(03):210-215.

[10] Ziongyuan,He Xiaoling.Stock price prediction method based on optimized LSTM model[J]. Statistics and Decision Making,2023,39(06):143-148.

[11] Gao Yuan,Huang Y.Stock price index prediction based on deep learning[J]. Software Engineering, 2024, 27(05): 7-13.

[12] Yin Haiyuan,Yang Qingsong.The impact of investor sentiment on stock price bubbles in stock bars based on Bi-LSTM model mining[J]. Journal of Management,2022,19(12):1874-1885.

[13] Wang Jiazeng. Research on stock price prediction and stock portfolio based on improved LSTM neural network[D].Xi'an University of Architecture and Technology,2023.2.2

[14] Little, W.A., 1974.The existence of persistent states in the brain. In From High-Temperature Superconductivity to Microminiature Refrigeration (pp. 145-164). Springer, Boston, MA.

[15] Hopfield, J.J.,1982.Neural networks and physical systems with emergent collective computational abilities. Proceedings of the national academy of sciences, 79(8), pp.2554-2558.

[16] Jordan, M.I.,1986. Serial order: A parallel distributed processing approach (Tech. Rep. No. 8604). San Diego: University of California, Institute for Cognitive Science.

[17] Elman, J.L.,1990. Finding structure in time. Cognitive science, 14(2), 179-211.

[18] Hochreiter S,Schmidhuber J.Long Short-term Memory[J].Neural Computation,1997,9(8):1735-1780.