IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2208.07232.html
   My bibliography  Save this paper

Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction

Author

Listed:
  • Lei Li
  • Zhiyuan Zhang
  • Ruihan Bao
  • Keiko Harimoto
  • Xu Sun

Abstract

Traditional knowledge distillation in classification problems transfers the knowledge via class correlations in the soft label produced by teacher models, which are not available in regression problems like stock trading volume prediction. To remedy this, we present a novel distillation framework for training a light-weight student model to perform trading volume prediction given historical transaction data. Specifically, we turn the regression model into a probabilistic forecasting model, by training models to predict a Gaussian distribution to which the trading volume belongs. The student model can thus learn from the teacher at a more informative distributional level, by matching its predicted distributions to that of the teacher. Two correlational distillation objectives are further introduced to encourage the student to produce consistent pair-wise relationships with the teacher model. We evaluate the framework on a real-world stock volume dataset with two different time window settings. Experiments demonstrate that our framework is superior to strong baseline models, compressing the model size by $5\times$ while maintaining $99.6\%$ prediction accuracy. The extensive analysis further reveals that our framework is more effective than vanilla distillation methods under low-resource scenarios.

Suggested Citation

  • Lei Li & Zhiyuan Zhang & Ruihan Bao & Keiko Harimoto & Xu Sun, 2022. "Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction," Papers 2208.07232, arXiv.org.
  • Handle: RePEc:arx:papers:2208.07232
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2208.07232
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Christian T. Brownlees & Fabrizio Cipollini & Giampiero M. Gallo, 2011. "Intra-daily Volume Modeling and Prediction for Algorithmic Trading," Journal of Financial Econometrics, Oxford University Press, vol. 9(3), pages 489-518, Summer.
    2. Salinas, David & Flunkert, Valentin & Gasthaus, Jan & Januschowski, Tim, 2020. "DeepAR: Probabilistic forecasting with autoregressive recurrent networks," International Journal of Forecasting, Elsevier, vol. 36(3), pages 1181-1191.
    3. Bialkowski, Jedrzej & Darolles, Serge & Le Fol, Gaëlle, 2008. "Improving VWAP strategies: A dynamic volume approach," Journal of Banking & Finance, Elsevier, vol. 32(9), pages 1709-1722, September.
    4. Nino Antulov-Fantulin & Tian Guo & Fabrizio Lillo, 2020. "Temporal mixture ensemble models for intraday volume forecasting in cryptocurrency exchange markets," Papers 2005.09356, arXiv.org, revised Dec 2020.
    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. Ferriani, Fabrizio, 2010. "Informed and uninformed traders at work: evidence from the French market," MPRA Paper 24487, University Library of Munich, Germany.
    2. Szűcs, Balázs Árpád, 2017. "Forecasting intraday volume: Comparison of two early models," Finance Research Letters, Elsevier, vol. 21(C), pages 249-258.
    3. Dutt, Tanuj & Humphery-Jenner, Mark, 2013. "Stock return volatility, operating performance and stock returns: International evidence on drivers of the ‘low volatility’ anomaly," Journal of Banking & Finance, Elsevier, vol. 37(3), pages 999-1017.
    4. Ye, Xunyu & Gao, Ping & Li, Handong, 2015. "Improving estimation of the fractionally differencing parameter in the SARFIMA model using tapered periodogram," Economic Modelling, Elsevier, vol. 46(C), pages 167-179.
    5. Ito, R., 2016. "Spline-DCS for Forecasting Trade Volume in High-Frequency Finance," Cambridge Working Papers in Economics 1606, Faculty of Economics, University of Cambridge.
    6. Roman Huptas, 2019. "Point forecasting of intraday volume using Bayesian autoregressive conditional volume models," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 38(4), pages 293-310, July.
    7. Francesco Calvori & Fabrizio Cipollini & Giampiero M. Gallo, 2014. "Go with the Flow: A GAS model for Predicting Intra-daily Volume Shares," Econometrics Working Papers Archive 2014_01, Universita' degli Studi di Firenze, Dipartimento di Statistica, Informatica, Applicazioni "G. Parenti", revised Feb 2014.
    8. Clements, Adam & Hurn, Stan & Volkov, Vladimir, 2021. "A simple linear alternative to multiplicative error models with an application to trading volume," Working Papers 2021-06, University of Tasmania, Tasmanian School of Business and Economics.
    9. Naimoli, Antonio & Storti, Giuseppe, 2019. "Heterogeneous component multiplicative error models for forecasting trading volumes," International Journal of Forecasting, Elsevier, vol. 35(4), pages 1332-1355.
    10. Spiliotis, Evangelos & Makridakis, Spyros & Kaltsounis, Anastasios & Assimakopoulos, Vassilios, 2021. "Product sales probabilistic forecasting: An empirical evaluation using the M5 competition data," International Journal of Production Economics, Elsevier, vol. 240(C).
    11. Taras Bodnar & Nikolaus Hautsch, 2012. "Copula-Based Dynamic Conditional Correlation Multiplicative Error Processes," SFB 649 Discussion Papers SFB649DP2012-044, Sonderforschungsbereich 649, Humboldt University, Berlin, Germany.
    12. Bojer, Casper Solheim & Meldgaard, Jens Peder, 2021. "Kaggle forecasting competitions: An overlooked learning opportunity," International Journal of Forecasting, Elsevier, vol. 37(2), pages 587-603.
    13. Ying Shu & Chengfu Ding & Lingbing Tao & Chentao Hu & Zhixin Tie, 2023. "Air Pollution Prediction Based on Discrete Wavelets and Deep Learning," Sustainability, MDPI, vol. 15(9), pages 1-19, April.
    14. Demetrio Lacava & Giampiero M. Gallo & Edoardo Otranto, 2022. "Unconventional policies effects on stock market volatility: The MAP approach," Journal of the Royal Statistical Society Series C, Royal Statistical Society, vol. 71(5), pages 1245-1265, November.
    15. Olivier Gu'eant & Guillaume Royer, 2013. "VWAP execution and guaranteed VWAP," Papers 1306.2832, arXiv.org, revised May 2014.
    16. Harvey,Andrew C., 2013. "Dynamic Models for Volatility and Heavy Tails," Cambridge Books, Cambridge University Press, number 9781107034723.
    17. Anna Almosova & Niek Andresen, 2023. "Nonlinear inflation forecasting with recurrent neural networks," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 42(2), pages 240-259, March.
    18. Philippe Goulet Coulombe & Mikael Frenette & Karin Klieber, 2023. "From Reactive to Proactive Volatility Modeling with Hemisphere Neural Networks," Working Papers 23-04, Chair in macroeconomics and forecasting, University of Quebec in Montreal's School of Management, revised Nov 2023.
    19. Vladimir Markov & Olga Vilenskaia & Vlad Rashkovich, 2019. "Quintet Volume Projection," Papers 1904.01412, arXiv.org.
    20. Ye Xunyu & Yan Rui & Li Handong, 2014. "Forecasting trading volume in the Chinese stock market based on the dynamic VWAP," Studies in Nonlinear Dynamics & Econometrics, De Gruyter, vol. 18(2), pages 1-20, April.

    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:2208.07232. 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.