Hybrid RNN-DQN Model for Time Series Forecasting and Trading Strategy Optimization
Keywords:
Hybrid Models, Recurrent Neural Networks, Deep Q-Networks, Time Series Forecasting, Trading Strategy Optimization, Financial Markets.Abstract
Deep learning techniques have attracted a lot of attention in the financial markets lately because of their potential for trading strategy optimization and asset price forecasting. In order to forecast time series and optimize trading strategy, this study presents a novel hybrid model that combines Recurrent Neural Networks (RNN) and Deep Networks (DQN). By combining the best features of DQNs for learning optimal action policies and RNNs for capturing temporal dependencies, the hybrid model improves performance and robustness in financial prediction and decision-making tasks. Our proposed hybrid model is able to anticipate asset values and provide profitable trading strategies, as evidenced by the experimental findings we report on a large dataset spanning multiple years of foreign exchange (forex) market data. Additionally, we perform thorough assessments and contrasts with conventional ways and independent deep learning models to verify the enhanced effectiveness and efficiency of the suggested hybrid model. Our research prepares the way for improved decision support systems and algorithmic trading methods in the field of quantitative finance by enhancing deep learning techniques in financial forecasting and trading.
Downloads
References
Zhang, Z., Zohren, S., & Roberts, S. (2019). Deep reinforcement learning for trading. arXiv preprint arXiv:1911.10107.
Cai, J., Du, A., Liang, X., & Li, S. (2023). Prediction-based path planning for safe and efficient human–robot collaboration in construction via deep reinforcement learning. Journal of Computing in Civil Engineering, 37(1), 04022046.
Hossain, M. A., Karim, R., Thulasiram, R., Bruce, N. D., & Wang, Y. (2018, November). Hybrid deep learning model for stock price prediction. In 2018 ieee symposium series on computational intelligence (ssci) (pp. 1837-1844). IEEE.
Torres, J. F., Hadjout, D., Sebaa, A., Martínez-Álvarez, F., &Troncoso, A. (2021). Deep learning for time series forecasting: a survey. Big Data, 9(1), 3-21.
Chiumera, D. J. (2022). Deep Reinforcement Learning for Quantitative Finance: Time Series Forecasting using Proximal Policy Optimization (Doctoral dissertation, Carleton University).
Thakkar, A., & Chaudhari, K. (2021). A comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions. Expert Systems with Applications, 177, 114800.
Liu, C., Yan, J., Guo, F., & Guo, M. (2022). Forecasting the market with machine learning algorithms: an application of NMC-BERT-LSTM-DQN-X algorithm in quantitative trading. ACM Transactions on Knowledge Discovery from Data (TKDD), 16(4), 1-22.
Liang, Z., Chen, H., Zhu, J., Jiang, K., & Li, Y. (2018). Adversarial deep reinforcement learning in portfolio management. arXiv preprint arXiv:1808.09940.
Jing, N., Wu, Z., & Wang, H. (2021). A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction. Expert Systems with Applications, 178, 115019.
Zhang, W., Zhang, N., Yan, J., Li, G., & Yang, X. (2022). Auto uning of price prediction models for high-frequency trading via reinforcement learning. Pattern Recognition, 125, 108543.
Zhang, W., Li, S., Guo, Z., & Yang, Y. (2023). A hybrid forecasting model based on deep learning feature extraction and statistical arbitrage methods for stock trading strategies. Journal of Forecasting, 42(7), 1729-1749.
Zhang, J., Zhai, J., & Wang, H. (2021). A survey on deep learning in financial markets. In Proceedings of the First International Forum on Financial Mathematics and Financial Technology (pp. 35-57). Springer Singapore.
Lu, W., Li, J., Li, Y., Sun, A., & Wang, J. (2020). A CNN-LSTM-based model to forecast stock prices. Complexity, 2020, 1-10.
Huang, G., Zhou, X., & Song, Q. (2020). Deep reinforcement learning for portfolio management. arXiv preprint arXiv:2012.13773.
Zhou, Q., Zhou, C., & Wang, X. (2022). Stock prediction based on bidirectional gated recurrent unit with convolutional neural network and feature selection. PloS one, 17(2), e0262501.
Liu, S., Wang, B., Li, H., Chen, C., & Wang, Z. (2023). Continual portfolio selection in dynamic environments via incremental reinforcement learning. International Journal of Machine Learning and Cybernetics, 14(1), 269-279.
Zhang, X., Zhong, C., &Abualigah, L. (2023). Foreign exchange forecasting and portfolio optimization strategy based on hybrid-molecular differential evolution algorithms. Soft Computing, 27(7), 3921-3939.
Fu, Y., Wu, D., & Boulet, B. (2022, June). Reinforcement learning based dynamic model combination for time series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 6, pp. 6639-6647).
Wu, N., Ke, Z., & Feng, L. (2022, July). Stock price forecast based on lstm and ddqn. In 2022 14th International Conference on Advanced Computational Intelligence (ICACI) (pp. 182-185). IEEE.
Hu, Zexin, Yiqi Zhao, and Matloob Khushi. 2021. "A Survey of Forex and Stock Price Prediction Using Deep Learning" Applied System Innovation 4, no. 1: 9. https://doi.org/10.3390/asi4010009.
Manujakshi, B. C., Kabadi, M. G., & Naik, N. (2022). A hybrid stock price prediction model based on pre and deep neural network. Data, 7(5), 51.
Srivinay, Manujakshi, B. C., Kabadi, M. G., & Naik, N. (2022). A hybrid stock price prediction model based on PRE and deep neural network. Data, 7(5), 51.
Kanwal, A., Lau, M. F., Ng, S. P., Sim, K. Y., & Chandrasekaran, S. (2022). BiCuDNNLSTM-1dCNN—A hybrid deep learning-based predictive model for stock price prediction. Expert Systems with Applications, 202, 117123.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.