IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2511.17963.html

Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization

Author

Listed:
  • Jun Kevin
  • Pujianto Yugopuspito

Abstract

This paper introduces a hybrid framework for portfolio optimization that fuses Long Short-Term Memory (LSTM) forecasting with a Proximal Policy Optimization (PPO) reinforcement learning strategy. The proposed system leverages the predictive power of deep recurrent networks to capture temporal dependencies, while the PPO agent adaptively refines portfolio allocations in continuous action spaces, allowing the system to anticipate trends while adjusting dynamically to market shifts. Using multi-asset datasets covering U.S. and Indonesian equities, U.S. Treasuries, and major cryptocurrencies from January 2018 to December 2024, the model is evaluated against several baselines, including equal-weight, index-style, and single-model variants (LSTM-only and PPO-only). The framework's performance is benchmarked against equal-weighted, index-based, and single-model approaches (LSTM-only and PPO-only) using annualized return, volatility, Sharpe ratio, and maximum drawdown metrics, each adjusted for transaction costs. The results indicate that the hybrid architecture delivers higher returns and stronger resilience under non-stationary market regimes, suggesting its promise as a robust, AI-driven framework for dynamic portfolio optimization.

Suggested Citation

  • Jun Kevin & Pujianto Yugopuspito, 2025. "Hybrid LSTM and PPO Networks for Dynamic Portfolio Optimization," Papers 2511.17963, arXiv.org.
    • Handle: RePEc:arx:papers:2511.17963
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2511.17963
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Li, Pengtao & Zhou, Kaile & Lu, Xinhui & Yang, Shanlin, 2020. "A hybrid deep learning model for short-term PV power forecasting," Applied Energy, Elsevier, vol. 259(C).
    2. Jonathan Sadighian, 2020. "Extending Deep Reinforcement Learning Frameworks in Cryptocurrency Market Making," Papers 2004.06985, arXiv.org.
    3. Bouteska, Ahmed & Abedin, Mohammad Zoynul & Hajek, Petr & Yuan, Kunpeng, 2024. "Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods," International Review of Financial Analysis, Elsevier, vol. 92(C).
    4. Harris, Richard D.F. & Mazibas, Murat & Rambaccussing, Dooruj, 2024. "Bitcoin replication using machine learning," International Review of Financial Analysis, Elsevier, vol. 93(C).
    5. Wei Bao & Jun Yue & Yulei Rao, 2017. "A deep learning framework for financial time series using stacked autoencoders and long-short term memory," PLOS ONE, Public Library of Science, vol. 12(7), pages 1-24, July.
    6. Nick James & Max Menzies, 2023. "Collective dynamics, diversification and optimal portfolio construction for cryptocurrencies," Papers 2304.08902, arXiv.org, revised Jun 2023.
    7. Wujun Lv & Tao Pang & Xiaobao Xia & Jingzhou Yan, 2023. "Dynamic portfolio choice with uncertain rare-events risk in stock and cryptocurrency markets," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 9(1), pages 1-28, December.
    8. Abdul Jabbar & Syed Qaisar Jalil, 2024. "A Comprehensive Analysis of Machine Learning Models for Algorithmic Trading of Bitcoin," Papers 2407.18334, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Dominik Stempie'n & Janusz Gajda, 2025. "Comparative analysis of financial data differentiation techniques using LSTM neural network," Papers 2505.19243, arXiv.org.
    2. Dominik Stempie'n & Robert 'Slepaczuk, 2025. "Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models," Papers 2505.19617, arXiv.org.
    3. Andrea Bucci, 2020. "Realized Volatility Forecasting with Neural Networks," Journal of Financial Econometrics, Oxford University Press, vol. 18(3), pages 502-531.
    4. Jaydip Sen & Sidra Mehtab & Abhishek Dutta & Saikat Mondal, 2022. "Precise Stock Price Prediction for Optimized Portfolio Design Using an LSTM Model," Papers 2203.01326, arXiv.org.
    5. Nosratabadi, Saeed & Mosavi, Amir & Duan, Puhong & Ghamisi, Pedram & Filip, Ferdinand & Band, Shahab S. & Reuter, Uwe & Gama, Joao & Gandomi, Amir H., 2020. "Data science in economics: comprehensive review of advanced machine learning and deep learning methods," FrenXiv e75gc_v1, Center for Open Science.
    6. Jaydip Sen & Sidra Mehtab, 2021. "Design and Analysis of Robust Deep Learning Models for Stock Price Prediction," Papers 2106.09664, arXiv.org.
    7. Khan, Waqas & Walker, Shalika & Zeiler, Wim, 2022. "Improved solar photovoltaic energy generation forecast using deep learning-based ensemble stacking approach," Energy, Elsevier, vol. 240(C).
    8. Hossein Ghanbari & Emran Mohammadi & Amir Mohammad Larni Fooeik & Ronald Ravinesh Kumar & Peter Josef Stauvermann & Mostafa Shabani, 2024. "Cryptocurrency Portfolio Allocation under Credibilistic CVaR Criterion and Practical Constraints," Risks, MDPI, vol. 12(10), pages 1-25, October.
    9. Umut Ugurlu & Ilkay Oksuz & Oktay Tas, 2018. "Electricity Price Forecasting Using Recurrent Neural Networks," Energies, MDPI, vol. 11(5), pages 1-23, May.
    10. Adebayo Oshingbesan & Eniola Ajiboye & Peruth Kamashazi & Timothy Mbaka, 2022. "Model-Free Reinforcement Learning for Asset Allocation," Papers 2209.10458, arXiv.org.
    11. repec:osf:thesis:auyvc_v1 is not listed on IDEAS
    12. He, Jing & Fu, Cheng & Ye, Shengchao, 2025. "Fine-grained poverty alleviation performance evaluation based on solar photovoltaic projects—A case study of Huoshan County, China," Energy, Elsevier, vol. 332(C).
    13. Elianne Mora & Jenny Cifuentes & Geovanny Marulanda, 2021. "Short-Term Forecasting of Wind Energy: A Comparison of Deep Learning Frameworks," Energies, MDPI, vol. 14(23), pages 1-26, November.
    14. Rian Dolphin & Barry Smyth & Ruihai Dong, 2024. "Contrastive Learning of Asset Embeddings from Financial Time Series," Papers 2407.18645, arXiv.org.
    15. Fayssal Jamhamed & Franck Martin & Fabien Rondeau & Josué Thélissaint & Stéphane Tufféry, 2024. "Regime-Specific Dynamics and Informational Efficiency in Cryptomarkets: Evidence from Gaussian Mixture Models," Economics Working Paper Archive (University of Rennes & University of Caen) 2024-13, Center for Research in Economics and Management (CREM), University of Rennes, University of Caen and CNRS.
    16. Junjie Guo, 2024. "Deep Learning in Long-Short Stock Portfolio Allocation: An Empirical Study," Papers 2411.13555, arXiv.org, revised Nov 2024.
    17. Tomoshiro Ochiai & Jose C. Nacher, 2020. "Unveiling the directional network behind the financial statements data using volatility constraint correlation," Papers 2008.07836, arXiv.org, revised Jun 2023.
    18. Doğan, Murat & Sayılır, Özlem & Komath, Muhammed Aslam Chelery & Çimen, Emre, 2025. "Prediction of market value of firms with corporate sustainability performance data using machine learning models," Finance Research Letters, Elsevier, vol. 77(C).
    19. Junyi Li & Xitong Wang & Yaoyang Lin & Arunesh Sinha & Micheal P. Wellman, 2020. "Generating Realistic Stock Market Order Streams," Papers 2006.04212, arXiv.org.
    20. Jaehoon Lee & Sang-Kyun Park & Salim Abdullah Bazher & Daewon Seo, 2025. "Development of a Fault Prediction Algorithm for Marine Propulsion Energy Storage System," Energies, MDPI, vol. 18(7), pages 1-18, March.
    21. James Wallbridge, 2020. "Transformers for Limit Order Books," Papers 2003.00130, arXiv.org.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2511.17963. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.