IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2303.07925.html
   My bibliography  Save this paper

Deep incremental learning models for financial temporal tabular datasets with distribution shifts

Author

Listed:
  • Thomas Wong
  • Mauricio Barahona

Abstract

We present a robust deep incremental learning framework for regression tasks on financial temporal tabular datasets which is built upon the incremental use of commonly available tabular and time series prediction models to adapt to distributional shifts typical of financial datasets. The framework uses a simple basic building block (decision trees) to build self-similar models of any required complexity to deliver robust performance under adverse situations such as regime changes, fat-tailed distributions, and low signal-to-noise ratios. As a detailed study, we demonstrate our scheme using XGBoost models trained on the Numerai dataset and show that a two layer deep ensemble of XGBoost models over different model snapshots delivers high quality predictions under different market regimes. We also show that the performance of XGBoost models with different number of boosting rounds in three scenarios (small, standard and large) is monotonically increasing with respect to model size and converges towards the generalisation upper bound. We also evaluate the robustness of the model under variability of different hyperparameters, such as model complexity and data sampling settings. Our model has low hardware requirements as no specialised neural architectures are used and each base model can be independently trained in parallel.

Suggested Citation

  • Thomas Wong & Mauricio Barahona, 2023. "Deep incremental learning models for financial temporal tabular datasets with distribution shifts," Papers 2303.07925, arXiv.org, revised Oct 2023.
  • Handle: RePEc:arx:papers:2303.07925
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2303.07925
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ivo Welch & Amit Goyal, 2008. "A Comprehensive Look at The Empirical Performance of Equity Premium Prediction," The Review of Financial Studies, Society for Financial Studies, vol. 21(4), pages 1455-1508, July.
    2. Antoine Didisheim & Bryan T. Kelly & Semyon Malamud, 2022. "Deep Regression Ensembles," Swiss Finance Institute Research Paper Series 22-20, Swiss Finance Institute.
    3. Y.C. Ho & D.L. Pepyne, 2002. "Simple Explanation of the No-Free-Lunch Theorem and Its Implications," Journal of Optimization Theory and Applications, Springer, vol. 115(3), pages 549-570, December.
    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. Hauzenberger, Niko & Huber, Florian & Klieber, Karin & Marcellino, Massimiliano, 2025. "Bayesian neural networks for macroeconomic analysis," Journal of Econometrics, Elsevier, vol. 249(PC).
    2. Faria, Gonçalo & Verona, Fabio, 2023. "Forecast combination in the frequency domain," Bank of Finland Research Discussion Papers 1/2023, Bank of Finland.
    3. Papapostolou, Nikos C. & Pouliasis, Panos K. & Nomikos, Nikos K. & Kyriakou, Ioannis, 2016. "Shipping investor sentiment and international stock return predictability," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 96(C), pages 81-94.
    4. Wang, Yubao & Huang, Xiaozhou & Huang, Zhendong, 2024. "Energy-related uncertainty and Chinese stock market returns," Finance Research Letters, Elsevier, vol. 62(PB).
    5. Su, Yuandong & Lu, Xinjie & Zeng, Qing & Huang, Dengshi, 2022. "Good air quality and stock market returns," Research in International Business and Finance, Elsevier, vol. 62(C).
    6. Zongwu Cai & Haiqiang Chen & Xiaosai Liao, 2020. "A New Robust Inference for Predictive Quantile Regression," WORKING PAPERS SERIES IN THEORETICAL AND APPLIED ECONOMICS 202002, University of Kansas, Department of Economics, revised Feb 2020.
    7. Salisu, Afees A. & Ademuyiwa, Idris & Isah, Kazeem O., 2018. "Revisiting the forecasting accuracy of Phillips curve: The role of oil price," Energy Economics, Elsevier, vol. 70(C), pages 334-356.
    8. Clark, Todd E. & McCracken, Michael W., 2012. "In-sample tests of predictive ability: A new approach," Journal of Econometrics, Elsevier, vol. 170(1), pages 1-14.
    9. Peñaranda, Francisco & Sentana, Enrique, 2016. "Duality in mean-variance frontiers with conditioning information," Journal of Empirical Finance, Elsevier, vol. 38(PB), pages 762-785.
    10. Fernando M. Duarte & Carlo Rosa, 2015. "The equity risk premium: a review of models," Economic Policy Review, Federal Reserve Bank of New York, issue 2, pages 39-57.
    11. Hou, Yang & Meng, Jiayin, 2018. "The momentum effect in the Chinese market and its relationship with the simultaneous and the lagged investor sentiment," MPRA Paper 94838, University Library of Munich, Germany.
    12. Ding, Jing & Jiang, Lei & Liu, Xiaohui & Peng, Liang, 2023. "Nonparametric tests for market timing ability using daily mutual fund returns," Journal of Economic Dynamics and Control, Elsevier, vol. 150(C).
    13. Yi, Yongsheng & Ma, Feng & Zhang, Yaojie & Huang, Dengshi, 2019. "Forecasting stock returns with cycle-decomposed predictors," International Review of Financial Analysis, Elsevier, vol. 64(C), pages 250-261.
    14. Nektarios Aslanidis & Charlotte Christiansen & Neophytos Lambertides & Christos S. Savva, 2019. "Idiosyncratic volatility puzzle: influence of macro-finance factors," Review of Quantitative Finance and Accounting, Springer, vol. 52(2), pages 381-401, February.
    15. Raushan Kumar, 2021. "Predicting Wheat Futures Prices in India," Asia-Pacific Financial Markets, Springer;Japanese Association of Financial Economics and Engineering, vol. 28(1), pages 121-140, March.
    16. Andrea Bucci, 2020. "Realized Volatility Forecasting with Neural Networks," Journal of Financial Econometrics, Oxford University Press, vol. 18(3), pages 502-531.
    17. Tsung-Jui Chiang-Lin & Yong-Shiuan Lee & Tzong-Hann Shieh & Chien-Chang Yen & Shang-Yueh Tsai, 2022. "Study of Asian indexes by a newly derived dynamic model," PLOS ONE, Public Library of Science, vol. 17(5), pages 1-19, May.
    18. Wu, Hanlin & Li, Pan & Cao, Jiawei & Xu, Zijian, 2024. "Forecasting the Chinese crude oil futures volatility using jump intensity and Markov-regime switching model," Energy Economics, Elsevier, vol. 134(C).
    19. Wen, Danyan & Liu, Li & Wang, Yudong & Zhang, Yaojie, 2022. "Forecasting crude oil market returns: Enhanced moving average technical indicators," Resources Policy, Elsevier, vol. 76(C).
    20. Angelo Aspris & Ester Félez‐Viñas & Sean Foley & Hamish Malloch & Jiri Svec, 2024. "The market risk premium in Australia: Forward‐looking evidence from the options market," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 64(4), pages 3951-3972, 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:2303.07925. 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.