Prediction of Stock Prices Based on the LSTM Model

DOI

10.2991/978-94-6463-142-5_42How to use a DOI?

Keywords

Long Short-Term Memory (LSTM); stock price forecast; time series; short-term price

Abstract

This paper focuses on improving the structure of the LSTM model and optimizing its parameters to improve its accuracy in predicting stock movements, as well as investigating the effectiveness of the LSTM neural network in predicting weekly and daily data for US stocks. On the one hand, the difference between the two models is analyzed and compared to verify the effect of different data sets on the prediction results; on the other hand, it provides suggestions on the selection of data sets for LSTM stock prediction research to ameliorate the accuracy of stock prediction. This study used a modified LSTM neural network model to predict stock price trends using a multi-series stock prediction method. The experimental results confirmed that the weekly data performed better than the daily data, with an average accuracy of 52.8% for the daily data and 58% for the weekly data, and the stock prediction accuracy was higher when the weekly data was used to train the LSTM model.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Guanze Shao
PY  - 2023
DA  - 2023/05/15
TI  - Prediction of Stock Prices Based on the LSTM Model
BT  - Proceedings of the 8th International Conference on Financial Innovation and Economic Development (ICFIED 2023)
PB  - Atlantis Press
SP  - 377
EP  - 387
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-142-5_42
DO  - 10.2991/978-94-6463-142-5_42
ID  - Shao2023
ER  -