IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2606.00143.html

Regime-Adaptive Continual Learning for Portfolio Management

Author

Listed:
  • Chaofan Pan
  • Lingfei Ren
  • Linbo Xiong
  • Yonghao Li
  • Wei Wei
  • Xin Yang

Abstract

Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective. Existing remedies, such as rolling-window retraining and naive online fine-tuning, are hindered by high computational costs and insufficient knowledge utilization, respectively, resulting in low returns and limited adaptability. Continual learning (CL) offers a promising paradigm by enabling trading agents to accumulate and transfer knowledge across sequential tasks. In this paper, we propose \textbf{Re}gime-aware \textbf{C}ontinual \textbf{A}daptive \textbf{P}ortfolio management (\textbf{ReCAP}), a novel framework that integrates CL into PM to address the challenges of dynamic financial environments. ReCAP employs an adaptive regime detection module to segment historical market data into variable-length regimes, enabling regime-specific learning of policy vectors and the construction of a policy library. During continual trading, a regime-gate module adaptively combines policy vectors from the library based on the current market state, facilitating rapid adaptation to newly detected regimes. Only the regime-gate and the current regime's policy vector are continually updated to preserve useful knowledge effectively. Extensive experiments on five real-world datasets demonstrate that ReCAP consistently outperforms popular baselines, achieving superior returns in long-term investment horizons and rapid adaptation to regime shifts.

Suggested Citation

  • Chaofan Pan & Lingfei Ren & Linbo Xiong & Yonghao Li & Wei Wei & Xin Yang, 2026. "Regime-Adaptive Continual Learning for Portfolio Management," Papers 2606.00143, arXiv.org.
  • Handle: RePEc:arx:papers:2606.00143
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2606.00143
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Stefano Giglio & Bryan Kelly & Dacheng Xiu, 2022. "Factor Models, Machine Learning, and Asset Pricing," Annual Review of Financial Economics, Annual Reviews, vol. 14(1), pages 337-368, November.
    2. Andrew Ang & Allan Timmermann, 2012. "Regime Changes and Financial Markets," Annual Review of Financial Economics, Annual Reviews, vol. 4(1), pages 313-337, October.
    3. David P. Helmbold & Robert E. Schapire & Yoram Singer & Manfred K. Warmuth, 1998. "On‐Line Portfolio Selection Using Multiplicative Updates," Mathematical Finance, Wiley Blackwell, vol. 8(4), pages 325-347, October.
    4. Guido Abate & Ignazio Basile & Pierpaolo Ferrari, 2024. "The integration of environmental, social and governance criteria in portfolio optimization: An empirical analysis," Corporate Social Responsibility and Environmental Management, John Wiley & Sons, vol. 31(3), pages 2054-2065, May.
    5. Kin‐Yip Ho & Kun Tracy Wang & Wanbin Walter Wang, 2023. "A novel approach to portfolio selection using news volume and sentiment," International Review of Finance, International Review of Finance Ltd., vol. 23(4), pages 903-917, December.
    6. Zhengyao Jiang & Dixing Xu & Jinjun Liang, 2017. "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem," Papers 1706.10059, arXiv.org, revised Jul 2017.
    7. Farzan Soleymani & Eric Paquet, 2021. "Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket," Papers 2105.08664, arXiv.org.
    8. Hoque, Mohammad Enamul & Soo-Wah, Low & Billah, Mabruk, 2023. "Time-frequency connectedness and spillover among carbon, climate, and energy futures: Determinants and portfolio risk management implications," Energy Economics, Elsevier, vol. 127(PB).
    9. Huntley Schaller & Simon Van Norden, 1997. "Regime switching in stock market returns," Applied Financial Economics, Taylor & Francis Journals, vol. 7(2), pages 177-191.
    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. Alexandre Carbonneau & Fr'ed'eric Godin, 2021. "Deep equal risk pricing of financial derivatives with non-translation invariant risk measures," Papers 2107.11340, arXiv.org.
    2. Ruxing Xu & Dan Wu & Ronghua Yi, 2016. "Pricing Cdss And Cds Options Under A Regime-Switching Cev Process With Jump To Default," ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH, Faculty of Economic Cybernetics, Statistics and Informatics, vol. 50(1), pages 253-271.
    3. Chatziantoniou, Ioannis & Filis, George & Floros, Christos, 2017. "Asset prices regime-switching and the role of inflation targeting monetary policy," Global Finance Journal, Elsevier, vol. 32(C), pages 97-112.
    4. Chauvet, Marcelle & Jiang, Cheng, 2023. "Nonlinear relationship between monetary policy and stock returns: Evidence from the U.S," Global Finance Journal, Elsevier, vol. 55(C).
    5. Muhammad Abro & Hassan Jaleel, 2026. "Regret-Driven Portfolios: LLM-Guided Smart Clustering for Optimal Allocation," Papers 2601.17021, arXiv.org.
    6. Frédérique Bec & Annabelle de Gaye, 2019. "Le modèle autorégressif autorégressif à seuil avec effet rebond : Une application aux rendements boursiers français et américains ," Working Papers hal-02014663, HAL.
    7. Shuo Sun & Rundong Wang & Bo An, 2021. "Reinforcement Learning for Quantitative Trading," Papers 2109.13851, arXiv.org.
    8. Zhang, Xiaoyuan & Zhang, Tianqi, 2022. "Barrier option pricing under a Markov Regime switching diffusion model," The Quarterly Review of Economics and Finance, Elsevier, vol. 86(C), pages 273-280.
    9. Focardi, Sergio M. & Fabozzi, Frank J. & Mazza, Davide, 2019. "Modeling local trends with regime shifting models with time-varying probabilities," International Review of Financial Analysis, Elsevier, vol. 66(C).
    10. Alexandre Carbonneau & Fr'ed'eric Godin, 2020. "Equal Risk Pricing of Derivatives with Deep Hedging," Papers 2002.08492, arXiv.org, revised Jun 2020.
    11. Ma, Cong & Nan, Shijing, 2024. "Dynamic graph reinforcement learning algorithm for portfolio management: A novel time–frequency correlated model," Finance Research Letters, Elsevier, vol. 63(C).
    12. Zeng, Songlin & Bec, Frédérique, 2015. "Do stock returns rebound after bear markets? An empirical analysis from five OECD countries," Journal of Empirical Finance, Elsevier, vol. 30(C), pages 50-61.
    13. Haase, Felix & Neuenkirch, Matthias, 2023. "Predictability of bull and bear markets: A new look at forecasting stock market regimes (and returns) in the US," International Journal of Forecasting, Elsevier, vol. 39(2), pages 587-605.
    14. Huanming Zhang & Zhengyong Jiang & Jionglong Su, 2021. "A Deep Deterministic Policy Gradient-based Strategy for Stocks Portfolio Management," Papers 2103.11455, arXiv.org.
    15. Hao Chen & Changxin Xu & Zhiliang Xu, 2025. "Integrating Weak Aggregating Algorithm and Reinforcement Learning for Online Portfolio Selection: The WARL Strategy," Computational Economics, Springer;Society for Computational Economics, vol. 66(3), pages 2001-2027, September.
    16. Massimo Guidolin, 2011. "Markov Switching Models in Empirical Finance," Advances in Econometrics, in: Missing Data Methods: Time-Series Methods and Applications, pages 1-86, Emerald Group Publishing Limited.
    17. Gabriel Nixon Raj, 2025. "Adaptive and Regime-Aware RL for Portfolio Optimization," Papers 2509.14385, arXiv.org.
    18. Wonsup Shin & Seok-Jun Bu & Sung-Bae Cho, 2019. "Automatic Financial Trading Agent for Low-risk Portfolio Management using Deep Reinforcement Learning," Papers 1909.03278, arXiv.org.
    19. Ziming Gao & Yuan Gao & Yi Hu & Zhengyong Jiang & Jionglong Su, 2020. "Application of Deep Q-Network in Portfolio Management," Papers 2003.06365, arXiv.org.
    20. Yu, Pengrui & Liu, Siya & Jin, Chengneng & Gu, Runsheng & Gong, Xiaomin, 2025. "Optimization-based spectral end-to-end deep reinforcement learning for equity portfolio management," Pacific-Basin Finance Journal, Elsevier, vol. 91(C).

    More about this item

    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:2606.00143. 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: https://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.