Stock Index Forecasting and Automated Trading System Based on LSTM-TCN Model
DOI:
https://doi.org/10.54097/zxsp7x87Keywords:
Quantitative Trading, Long Short-Term Memory (LSTM), Time Series Convolutional Network (TCN), Signal Generation, Trailing StopAbstract
Currently, traditional models, like ARIMA, can hardly capture long-term dependencies and local volatility patterns of stock index time series simultaneously. Under this circumstance, this article constructs an LSTM+TCN automatic trading system for Hang Seng Index, NASDAQ Composite Index and Nikkei 225 Index. This system uses processed technical indicators, which can be obtained from the raw data directly, as feature engineering. Then, it predicts the direction and fluctuation magnitude of the first and the third days separately, and generates trading signals through a consensus mecha-nism among three branches. With a trailing stop strategy, the system shows a great trading performance in the back-test, even though the results of the prediction layer are not really ideal.
Downloads
References
[1] Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054. DOI: https://doi.org/10.1016/j.ejor.2017.11.054
[2] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735. DOI: https://doi.org/10.1162/neco.1997.9.8.1735
[3] Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271. https://doi.org/10.48550/arXiv.1803.01271.
[4] Hu, Z., Zhao, Y., & Khushi, M. (2021). A survey of forex and stock price prediction using deep learning. Applied System Innovation, 4(1), 9. https://doi.org/10.3390/asi4010009. DOI: https://doi.org/10.3390/asi4010009
[5] Lin, C. C., & Marques, J. A. L. (2024). Stock market prediction using artificial intelligence: A systematic review of systematic reviews. Social Sciences & Humanities Open, 9, 100864. https://doi.org/10.1016/j.ssaho.2024.100864. DOI: https://doi.org/10.1016/j.ssaho.2024.100864
[6] Aadhitya, A., Rajapriya, R., Vineetha, R. S., & Bagde, A. M. (2023). Predicting stock market time-series data using CNN-LSTM neural network model. arXiv preprint arXiv:2305.14378. https://doi.org/10.48550/arXiv.2305.14378.
[7] Dai, W., Wu, J., Zhang, X., et al. (2021). Price change prediction of ultra-high-frequency financial data based on temporal convolutional network. Expert Systems with Applications, 182, 115235. https://doi.org/10.1016/j.eswa.2021.115235. DOI: https://doi.org/10.1016/j.eswa.2021.115235
[8] Luo, D., & Wang, X. (2024). ModernTCN: A modern pure convolution structure for general time series analysis. arXiv preprint arXiv:2403.01493. https://doi.org/10.48550/arXiv.2403.01493.
[9] Wen, R., Torkkola, K., Narayanaswamy, B., & Madeka, D. (2017). A multi-horizon quantile recurrent forecaster. arXiv preprint arXiv:1711.11053. https://doi.org/10.48550/arXiv.1711.11053.
[10] López de Prado, M. (2018). Advances in financial machine learning. Wiley. DOI: https://doi.org/10.2139/ssrn.3365271
[11] Zong, C., Shao, J., Lu, W., & Zhuang, Y. (2024). Stock movement prediction with multimodal stable fusion via gated cross-attention mechanism. arXiv preprint arXiv:2406.06594. https://doi.org/10.48550/arXiv.2406.06594. DOI: https://doi.org/10.1007/s40747-025-02023-3
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
