IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2603.19288.html

Joint Return and Risk Modeling with Deep Neural Networks for Portfolio Construction

Author

Listed:
  • Keonvin Park

Abstract

Portfolio construction traditionally relies on separately estimating expected returns and covariance matrices using historical statistics, often leading to suboptimal allocation under time-varying market conditions. This paper proposes a joint return and risk modeling framework based on deep neural networks that enables end-to-end learning of dynamic expected returns and risk structures from sequential financial data. Using daily data from ten large-cap US equities spanning 2010 to 2024, the proposed model is evaluated across return prediction, risk estimation, and portfolio-level performance. Out-of-sample results during 2020 to 2024 show that the deep forecasting model achieves competitive predictive accuracy (RMSE = 0.0264) with economically meaningful directional accuracy (51.9%). More importantly, the learned representation effectively captures volatility clustering and regime shifts. When integrated into portfolio optimization, the proposed Neural Portfolio strategy achieves an annual return of 36.4% and a Sharpe ratio of 0.91, outperforming equal weight and historical mean-variance benchmarks in terms of risk-adjusted performance. These findings demonstrate that jointly modeling return and covariance dynamics can provide consistent improvements over traditional allocation approaches. The framework offers a scalable and practical alternative for data-driven portfolio construction under nonstationary market conditions.

Suggested Citation

  • Keonvin Park, 2026. "Joint Return and Risk Modeling with Deep Neural Networks for Portfolio Construction," Papers 2603.19288, arXiv.org.
  • Handle: RePEc:arx:papers:2603.19288
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2603.19288
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Matthew Dixon & Diego Klabjan & Jin Hoon Bang, 2017. "Classification-based financial markets prediction using deep neural networks," Algorithmic Finance, IOS Press, vol. 6(3-4), pages 67-77.
    2. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," Review of Finance, European Finance Association, vol. 33(5), pages 2223-2273.
    3. Bollerslev, Tim, 1986. "Generalized autoregressive conditional heteroskedasticity," Journal of Econometrics, Elsevier, vol. 31(3), pages 307-327, April.
    4. Ledoit, Olivier & Wolf, Michael, 2004. "A well-conditioned estimator for large-dimensional covariance matrices," Journal of Multivariate Analysis, Elsevier, vol. 88(2), pages 365-411, February.
    5. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," The Review of Financial Studies, Society for Financial Studies, vol. 33(5), pages 2223-2273.
    6. Fischer, Thomas & Krauss, Christopher, 2018. "Deep learning with long short-term memory networks for financial market predictions," European Journal of Operational Research, Elsevier, vol. 270(2), pages 654-669.
    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. Andrés García-Medina & Ester Aguayo-Moreno, 2024. "LSTM–GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios," Computational Economics, Springer;Society for Computational Economics, vol. 63(4), pages 1511-1542, April.
    2. Conlon, Thomas & Cotter, John & Kynigakis, Iason, 2025. "Asset allocation with factor-based covariance matrices," European Journal of Operational Research, Elsevier, vol. 325(1), pages 189-203.
    3. Marcos López de Prado & Joseph Simonian & Francesco A. Fabozzi & Frank J. Fabozzi, 2025. "Enhancing Markowitz's portfolio selection paradigm with machine learning," Annals of Operations Research, Springer, vol. 346(1), pages 319-340, March.
    4. Abraham Itzhak Weinberg, 2025. "Hybrid Quantum-Classical Ensemble Learning for S\&P 500 Directional Prediction," Papers 2512.15738, arXiv.org.
    5. Rad, Hossein & Low, Rand Kwong Yew & Miffre, Joëlle & Faff, Robert, 2023. "The commodity risk premium and neural networks," Journal of Empirical Finance, Elsevier, vol. 74(C).
    6. Kim Christensen & Mathias Siggaard & Bezirgen Veliyev, 2023. "A Machine Learning Approach to Volatility Forecasting," Journal of Financial Econometrics, Oxford University Press, vol. 21(5), pages 1680-1727.
    7. Adrian Fernandez-Perez & Ana-Maria Fuertes & Joëlle Miffre, 2026. "Does Speculation in Futures Markets Improve Commodity Hedging Decisions?," Management Science, INFORMS, vol. 72(3), pages 2525-2544, March.
    8. Wang, Yuejing & Ye, Wuyi & Jiang, Ying & Liu, Xiaoquan, 2024. "Volatility prediction for the energy sector with economic determinants: Evidence from a hybrid model," International Review of Financial Analysis, Elsevier, vol. 92(C).
    9. Qian, Yihe & Zhang, Yang, 2025. "Long-term forecasting in asset pricing: Machine learning models’ sensitivity to macroeconomic shifts and firm-specific factors," The North American Journal of Economics and Finance, Elsevier, vol. 78(C).
    10. Paul Handro & Bogdan Dima, 2024. "Analyzing Financial Markets Efficiency: Insights from a Bibliometric and Content Review," Journal of Financial Studies, Institute of Financial Studies, vol. 16(9), pages 119-175, May.
    11. Sun, Chuting & Wu, Qi & Yan, Xing, 2024. "Dynamic CVaR portfolio construction with attention-powered generative factor learning," Journal of Economic Dynamics and Control, Elsevier, vol. 160(C).
    12. Xue Gong & Weiguo Zhang & Yuan Zhao & Xin Ye, 2023. "Forecasting stock volatility with a large set of predictors: A new forecast combination method," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 42(7), pages 1622-1647, November.
    13. Merve Mert Sarıtaş, 2025. "Forecasting the XBANK Index in Türkiye Using Macroeconomic Indicators: A Model Comparison with Ensemble Learning Methods," International Econometric Review (IER), Economic Research Association, vol. 17(1), pages 44-58, June.
    14. Rubesam, Alexandre, 2022. "Machine learning portfolios with equal risk contributions: Evidence from the Brazilian market," Emerging Markets Review, Elsevier, vol. 51(PB).
    15. Barua, Ronil & Sharma, Anil K., 2023. "Using fear, greed and machine learning for optimizing global portfolios: A Black-Litterman approach," Finance Research Letters, Elsevier, vol. 58(PC).
    16. Tu, Xueyong & Li, Bin, 2024. "Robust portfolio selection with smart return prediction," Economic Modelling, Elsevier, vol. 135(C).
    17. Maung, Kenwin & Swanson, Norman R., 2025. "A survey of models and methods used for forecasting when investing in financial markets," International Journal of Forecasting, Elsevier, vol. 41(4), pages 1355-1382.
    18. Junjie Guo, 2025. "Integration of Wavelet Transform Convolution and Channel Attention with LSTM for Stock Price Prediction based Portfolio Allocation," Papers 2507.01973, arXiv.org, revised Jul 2025.
    19. Huang, Xinyu & Newton, David P. & Platanakis, Emmanouil & Sutcliffe, Charles, 2025. "Single-stage portfolio optimization with automated machine learning for M6," International Journal of Forecasting, Elsevier, vol. 41(4), pages 1450-1460.
    20. Sergio Consoli & Luca Tiozzo Pezzoli & Elisa Tosetti, 2022. "Neural forecasting of the Italian sovereign bond market with economic news," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 185(S2), pages 197-224, December.

    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:2603.19288. 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.