IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2510.03129.html
   My bibliography  Save this paper

Signature-Informed Transformer for Asset Allocation

Author

Listed:
  • Yoontae Hwang
  • Stefan Zohren

Abstract

Robust asset allocation is a key challenge in quantitative finance, where deep-learning forecasters often fail due to objective mismatch and error amplification. We introduce the Signature-Informed Transformer (SIT), a novel framework that learns end-to-end allocation policies by directly optimizing a risk-aware financial objective. SIT's core innovations include path signatures for a rich geometric representation of asset dynamics and a signature-augmented attention mechanism embedding financial inductive biases, like lead-lag effects, into the model. Evaluated on daily S\&P 100 equity data, SIT decisively outperforms traditional and deep-learning baselines, especially when compared to predict-then-optimize models. These results indicate that portfolio-aware objectives and geometry-aware inductive biases are essential for risk-aware capital allocation in machine-learning systems. The code is available at: https://github.com/Yoontae6719/Signature-Informed-Transformer-For-Asset-Allocation

Suggested Citation

  • Yoontae Hwang & Stefan Zohren, 2025. "Signature-Informed Transformer for Asset Allocation," Papers 2510.03129, arXiv.org.
    • Handle: RePEc:arx:papers:2510.03129
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2510.03129
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yoontae Hwang & Yaxuan Kong & Stefan Zohren & Yongjae Lee, 2025. "Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization," Papers 2502.00828, arXiv.org.
    2. Deborah Miori & Mihai Cucuringu, 2022. "Returns-Driven Macro Regimes and Characteristic Lead-Lag Behaviour between Asset Classes," Papers 2209.00268, arXiv.org, revised Sep 2022.
    3. R. Cont, 2001. "Empirical properties of asset returns: stylized facts and statistical issues," Quantitative Finance, Taylor & Francis Journals, vol. 1(2), pages 223-236.
    4. Munki Chung & Yongjae Lee & Jang Ho Kim & Woo Chang Kim & Frank J. Fabozzi, 2022. "The effects of errors in means, variances, and correlations on the mean-variance framework," Quantitative Finance, Taylor & Francis Journals, vol. 22(10), pages 1893-1903, October.
    5. Fama, Eugene F, 1970. "Efficient Capital Markets: A Review of Theory and Empirical Work," Journal of Finance, American Finance Association, vol. 25(2), pages 383-417, May.
    6. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    7. 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. Muchnik, Lev & Bunde, Armin & Havlin, Shlomo, 2009. "Long term memory in extreme returns of financial time series," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 388(19), pages 4145-4150.
    2. Dima, Bogdan & Dima, Ştefana Maria & Ioan, Roxana, 2025. "The short-run impact of investor expectations’ past volatility on current predictions: The case of VIX," Journal of International Financial Markets, Institutions and Money, Elsevier, vol. 98(C).
    3. Bariviera, Aurelio F. & Font-Ferrer, Alejandro & Sorrosal-Forradellas, M. Teresa & Rosso, Osvaldo A., 2019. "An information theory perspective on the informational efficiency of gold price," The North American Journal of Economics and Finance, Elsevier, vol. 50(C).
    4. Klein, A. & Urbig, D. & Kirn, S., 2008. "Who Drives the Market? Estimating a Heterogeneous Agent-based Financial Market Model Using a Neural Network Approach," MPRA Paper 14433, University Library of Munich, Germany.
    5. David Vidal-Tomás & Simone Alfarano, 2020. "An agent-based early warning indicator for financial market instability," Journal of Economic Interaction and Coordination, Springer;Society for Economic Science with Heterogeneous Interacting Agents, vol. 15(1), pages 49-87, January.
    6. Bartosz Bieganowski & Robert 'Slepaczuk, 2024. "Supervised Autoencoders with Fractionally Differentiated Features and Triple Barrier Labelling Enhance Predictions on Noisy Data," Papers 2411.12753, arXiv.org, revised Nov 2024.
    7. Semei Coronado-Ram'irez & Pedro Celso-Arellano & Omar Rojas, 2014. "Adaptive Market Efficiency of Agricultural Commodity Futures Contracts," Papers 1412.8017, arXiv.org, revised Mar 2015.
    8. Kentaro Imajo & Kentaro Minami & Katsuya Ito & Kei Nakagawa, 2020. "Deep Portfolio Optimization via Distributional Prediction of Residual Factors," Papers 2012.07245, arXiv.org.
    9. Sandrine Jacob Leal & Mauro Napoletano & Andrea Roventini & Giorgio Fagiolo, 2016. "Rock around the clock: An agent-based model of low- and high-frequency trading," Journal of Evolutionary Economics, Springer, vol. 26(1), pages 49-76, March.
    10. Makowiec, D. & Gnaciński, P. & Miklaszewski, W., 2004. "Amplified imitation in percolation model of stock market," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 331(1), pages 269-278.
    11. Kei Nakagawa & Masanori Hirano & Kentaro Minami & Takanobu Mizuta, 2024. "A Multi-agent Market Model Can Explain the Impact of AI Traders in Financial Markets -- A New Microfoundations of GARCH model," Papers 2409.12516, arXiv.org.
    12. Ali Atiah Alzahrani, 2025. "Multi-Agent Regime-Conditioned Diffusion (MARCD) for CVaR-Constrained Portfolio Decisions," Papers 2510.10807, arXiv.org, revised Nov 2025.
    13. Neto, David, 2021. "Are Google searches making the Bitcoin market run amok? A tail event analysis," The North American Journal of Economics and Finance, Elsevier, vol. 57(C).
    14. Przemys{l}aw Rola, 2025. "Boltzmann Price: Toward Understanding the Fair Price in High-Frequency Markets," Papers 2507.09734, arXiv.org.
    15. Oussama Tilfani & My Youssef El Boukfaoui, 2020. "Multifractal Analysis of African Stock Markets During the 2007–2008 US Crisis," Review of Pacific Basin Financial Markets and Policies (RPBFMP), World Scientific Publishing Co. Pte. Ltd., vol. 22(04), pages 1-31, January.
    16. Amin Aminimehr & Ali Raoofi & Akbar Aminimehr & Amirhossein Aminimehr, 2022. "A Comprehensive Study of Market Prediction from Efficient Market Hypothesis up to Late Intelligent Market Prediction Approaches," Computational Economics, Springer;Society for Computational Economics, vol. 60(2), pages 781-815, August.
    17. Yudong Wang & Chongfeng Wu, 2013. "Efficiency of Crude Oil Futures Markets: New Evidence from Multifractal Detrending Moving Average Analysis," Computational Economics, Springer;Society for Computational Economics, vol. 42(4), pages 393-414, December.
    18. 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.
    19. Junshu Jiang & Jordan Richards & Raphael Huser & David Bolin, 2024. "The Efficient Tail Hypothesis: An Extreme Value Perspective on Market Efficiency," Papers 2408.06661, arXiv.org, revised Jul 2025.
    20. Torsten Trimborn & Philipp Otte & Simon Cramer & Maximilian Beikirch & Emma Pabich & Martin Frank, 2020. "SABCEMM: A Simulator for Agent-Based Computational Economic Market Models," Computational Economics, Springer;Society for Computational Economics, vol. 55(2), pages 707-744, February.

    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:2510.03129. 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.