Temporal Dynamics of AI Stock Prices: An LSTM Network Analysis

DOI

10.2991/978-94-6463-823-3_81How to use a DOI?

Keywords

LSTM; Stock; Machine Learning

Abstract

The methods of machine learning have become the core tool in the financial market with the advancement of artificial intelligence (AI). Among these models of machine learning, the Long Short-Term Memory (LSTM) network stands out due to its gating mechanism and ability to capture long-term dependencies. This study uses NVIDIA stock as a representative sample of the AI stock to construct a layered bidirectional LSTM model that integrates historical stock prices, trading volumes, and technical indicators, aiming to enhance the accuracy and robustness of AI stock price predictions. By using the 30-day sliding window techniques to turn the original data set into a supervised machine learning format, and through the min-max standardization to eliminate the dimensional difference. As a result, the LSTM performs well in regular fluctuations, but in circumstances where there is a sudden switch to high volatility, the model’s accuracy declines. This research optimized the pure LSTM model to enhance its ability to model complex financial data and demonstrated the significant advantage of the LSTM model in the steady market phase through cross-model evaluation with the random forest model and the Autoregressive Integrated Moving Average (ARIMA) model.

Copyright

© 2025 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  - Fengqingyang Hu
PY  - 2025
DA  - 2025/08/31
TI  - Temporal Dynamics of AI Stock Prices: An LSTM Network Analysis
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 813
EP  - 821
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_81
DO  - 10.2991/978-94-6463-823-3_81
ID  - Hu2025
ER  -