Regime-Sensitive BiLSTM-CNN for Predicting Stock Prices: A Tesla Case Study

DOI

10.2991/978-94-6463-823-3_29How to use a DOI?

Keywords

Bidirectional Long-Short Term Memory model; Convolutional Neural Networks; regime-aware neural network; RSI technical indicators; QLIKE loss function

Abstract

Predicting stock prices is a persistent challenge in financial markets. The time series data is intricate and non-linear, and market regimes are highly volatile. Traditional statistical models often struggle to capture the dynamic patterns in stock prices, while deep learning methods face difficulties in adapting to sudden market changes. This research aims to fill these gaps by developing a regime-aware neural network, which can improve the accuracy and robustness of stock price forecasting. Specifically, this study focuses on highly volatile technology stocks. A Bidirectional Long-Short Term Memory (BiLSTM) model combined with Convolutional Neural Networks (CNN) is proposed, integrated with volatility-adaptive dynamic batching, Relative Strength Index (RSI) technical indicators, and the QLIKE loss function. The framework adopts strict temporal partitioning and forward-looking normalization. Tests on TSLA data show that the model achieves a directional accuracy of 50.57% and a Q-like loss of 0.0106. The regime-aware BiLSTM-CNN neural network can effectively predict stock prices, establish a new benchmark for volatility-sensitive evaluation, and offer practical references for Tesla’s price trends.

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  - Zihang Zhang
PY  - 2025
DA  - 2025/08/31
TI  - Regime-Sensitive BiLSTM-CNN for Predicting Stock Prices: A Tesla Case Study
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 300
EP  - 307
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_29
DO  - 10.2991/978-94-6463-823-3_29
ID  - Zhang2025
ER  -