IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2410.22346.html
   My bibliography  Save this paper

Representation Learning for Regime detection in Block Hierarchical Financial Markets

Author

Listed:
  • Alexa Orton
  • Tim Gebbie

Abstract

We consider financial market regime detection from the perspective of deep representation learning of the causal information geometry underpinning traded asset systems using a hierarchical correlation structure to characterise market evolution. We assess the robustness of three toy models: SPDNet, SPD-NetBN and U-SPDNet whose architectures respect the underlying Riemannian manifold of input block hierarchical SPD correlation matrices. Market phase detection for each model is carried out using three data configurations: randomised JSE Top 60 data, synthetically-generated block hierarchical SPD matrices and block-resampled chronology-preserving JSE Top 60 data. We show that using a singular performance metric is misleading in our financial market investment use cases where deep learning models overfit in learning spatio-temporal correlation dynamics.

Suggested Citation

  • Alexa Orton & Tim Gebbie, 2024. "Representation Learning for Regime detection in Block Hierarchical Financial Markets," Papers 2410.22346, arXiv.org.
    • Handle: RePEc:arx:papers:2410.22346
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2410.22346
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Christian Borghesi & Matteo Marsili & Salvatore Miccich`e, 2007. "Emergence of time-horizon invariant correlation structure in financial returns by subtraction of the market mode," Papers physics/0702106, 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. Gautier Marti & Frank Nielsen & Philippe Donnat & S'ebastien Andler, 2016. "On clustering financial time series: a need for distances between dependent random variables," Papers 1603.07822, 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. Gautier Marti & Frank Nielsen & Miko{l}aj Bi'nkowski & Philippe Donnat, 2017. "A review of two decades of correlations, hierarchies, networks and clustering in financial markets," Papers 1703.00485, arXiv.org, revised Nov 2020.
    2. Sebastiano Michele Zema & Giorgio Fagiolo & Tiziano Squartini & Diego Garlaschelli, 2021. "Mesoscopic Structure of the Stock Market and Portfolio Optimization," Papers 2112.06544, arXiv.org.
    3. Michelle B Graczyk & Sílvio M Duarte Queirós, 2017. "Intraday seasonalities and nonstationarity of trading volume in financial markets: Collective features," PLOS ONE, Public Library of Science, vol. 12(7), pages 1-23, July.
    4. Sandoval, Leonidas, 2014. "To lag or not to lag? How to compare indices of stock markets that operate on different times," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 403(C), pages 227-243.
    5. Nicoló Musmeci & Tomaso Aste & T Di Matteo, 2015. "Relation between Financial Market Structure and the Real Economy: Comparison between Clustering Methods," PLOS ONE, Public Library of Science, vol. 10(3), pages 1-24, March.
    6. Leonidas Sandoval Junior, 2011. "Cluster formation and evolution in networks of financial market indices," Papers 1111.5069, arXiv.org.
    7. Marsili, Matteo & Raffaelli, Giacomo & Ponsot, Benedicte, 2009. "Dynamic instability in generic model of multi-assets markets," Journal of Economic Dynamics and Control, Elsevier, vol. 33(5), pages 1170-1181, May.
    8. Nava, Noemi & Di Matteo, T. & Aste, Tomaso, 2018. "Dynamic correlations at different time-scales with empirical mode decomposition," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 502(C), pages 534-544.
    9. Mesrop T. Mesropyan & Vardan G. Bardakhchyan, 2022. "Hellinger distance to normal distribution as market invariant," Papers 2206.05705, arXiv.org.
    10. Ajay Singh & Dinghai Xu, 2016. "Random matrix application to correlations amongst the volatility of assets," Quantitative Finance, Taylor & Francis Journals, vol. 16(1), pages 69-83, January.
    11. Musmeci, Nicoló & Aste, Tomaso & Di Matteo, T., 2015. "Relation between financial market structure and the real economy: comparison between clustering methods," LSE Research Online Documents on Economics 61644, London School of Economics and Political Science, LSE Library.
    12. Nicol'o Musmeci & Tomaso Aste & Tiziana Di Matteo, 2014. "Risk diversification: a study of persistence with a filtered correlation-network approach," Papers 1410.5621, arXiv.org.
    13. Radhakrishnan, Srinivasan & Duvvuru, Arjun & Sultornsanee, Sivarit & Kamarthi, Sagar, 2016. "Phase synchronization based minimum spanning trees for analysis of financial time series with nonlinear correlations," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 444(C), pages 259-270.
    14. Cheong, Siew Ann & Fornia, Robert Paulo & Lee, Gladys Hui Ting & Kok, Jun Liang & Yim, Woei Shyr & Xu, Danny Yuan & Zhang, Yiting, 2011. "The Japanese economy in crises: A time series segmentation study," Economics Discussion Papers 2011-24, Kiel Institute for the World Economy (IfW Kiel).
    15. Chester Curme & Michele Tumminello & Rosario N. Mantegna & H. Eugene Stanley & Dror Y. Kenett, 2015. "Emergence of statistically validated financial intraday lead-lag relationships," Quantitative Finance, Taylor & Francis Journals, vol. 15(8), pages 1375-1386, August.
    16. Sensoy, Ahmet & Tabak, Benjamin M., 2014. "Dynamic spanning trees in stock market networks: The case of Asia-Pacific," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 414(C), pages 387-402.
    17. Nicolo Musmeci & Tomaso Aste & Tiziana Di Matteo, 2014. "Relation between Financial Market Structure and the Real Economy: Comparison between Clustering Methods," Papers 1406.0496, arXiv.org, revised Jan 2015.
    18. Iacopo Mastromatteo & Matteo Marsili & Patrick Zoi, 2010. "Financial correlations at ultra-high frequency: theoretical models and empirical estimation," Papers 1011.1011, arXiv.org, revised Feb 2011.
    19. Sandoval, Leonidas Junior, 2013. "To lag or not to lag? How to compare indices of stock markets that operate at different times," Insper Working Papers wpe_319, Insper Working Paper, Insper Instituto de Ensino e Pesquisa.
    20. 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.

    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:2410.22346. 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.