IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2207.11577.html
   My bibliography  Save this paper

Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification

Author

Listed:
  • Mostafa Shabani
  • Dat Thanh Tran
  • Juho Kanniainen
  • Alexandros Iosifidis

Abstract

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly applied to another market or security due to differences inherent in the market conditions. In addition, as the market evolves through time, it is necessary to update the existing models or train new ones when new data is made available. This scenario, which is inherent in most financial forecasting applications, naturally raises the following research question: How to efficiently adapt a pre-trained model to a new set of data while retaining performance on the old data, especially when the old data is not accessible? In this paper, we propose a method to efficiently retain the knowledge available in a neural network pre-trained on a set of securities and adapt it to achieve high performance in new ones. In our method, the prior knowledge encoded in a pre-trained neural network is maintained by keeping existing connections fixed, and this knowledge is adjusted for the new securities by a set of augmented connections, which are optimized using the new data. The auxiliary connections are constrained to be of low rank. This not only allows us to rapidly optimize for the new task but also reduces the storage and run-time complexity during the deployment phase. The efficiency of our approach is empirically validated in the stock mid-price movement prediction problem using a large-scale limit order book dataset. Experimental results show that our approach enhances prediction performance as well as reduces the overall number of network parameters.

Suggested Citation

  • Mostafa Shabani & Dat Thanh Tran & Juho Kanniainen & Alexandros Iosifidis, 2022. "Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification," Papers 2207.11577, arXiv.org.
  • Handle: RePEc:arx:papers:2207.11577
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2207.11577
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Justin A. Sirignano, 2019. "Deep learning for limit order books," Quantitative Finance, Taylor & Francis Journals, vol. 19(4), pages 549-570, April.
    2. Dat Thanh Tran & Juho Kanniainen & Moncef Gabbouj & Alexandros Iosifidis, 2021. "Bilinear Input Normalization for Neural Networks in Financial Forecasting," Papers 2109.00983, arXiv.org.
    3. Adriano Koshiyama & Sebastian Flennerhag & Stefano B. Blumberg & Nick Firoozye & Philip Treleaven, 2020. "QuantNet: Transferring Learning Across Systematic Trading Strategies," Papers 2004.03445, arXiv.org, revised Jun 2020.
    4. Matthew F Dixon, 2017. "Sequence Classification of the Limit Order Book using Recurrent Neural Networks," Papers 1707.05642, arXiv.org.
    5. Kabin Kanjamapornkul & Richard Pinv{c}'ak & Sanphet Chunithpaisan & Erik Bartov{s}, 2017. "Support Spinor Machine," Papers 1709.03943, 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. Michael Karpe, 2020. "An overall view of key problems in algorithmic trading and recent progress," Papers 2006.05515, arXiv.org.
    2. Antonio Briola & Silvia Bartolucci & Tomaso Aste, 2024. "Deep Limit Order Book Forecasting," Papers 2403.09267, arXiv.org, revised Mar 2024.
    3. Matthew F Dixon, 2017. "A High Frequency Trade Execution Model for Supervised Learning," Papers 1710.03870, arXiv.org, revised Dec 2017.
    4. Xianfeng Jiao & Zizhong Li & Chang Xu & Yang Liu & Weiqing Liu & Jiang Bian, 2023. "Microstructure-Empowered Stock Factor Extraction and Utilization," Papers 2308.08135, arXiv.org.
    5. Andrea Coletta & Joseph Jerome & Rahul Savani & Svitlana Vyetrenko, 2023. "Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness," Papers 2306.12806, arXiv.org.
    6. Zihao Zhang & Stefan Zohren & Stephen Roberts, 2018. "DeepLOB: Deep Convolutional Neural Networks for Limit Order Books," Papers 1808.03668, arXiv.org, revised Jan 2020.
    7. Yufei Wu & Mahmoud Mahfouz & Daniele Magazzeni & Manuela Veloso, 2021. "How Robust are Limit Order Book Representations under Data Perturbation?," Papers 2110.04752, arXiv.org.
    8. Hyejung Chung & Kyung-shik Shin, 2018. "Genetic Algorithm-Optimized Long Short-Term Memory Network for Stock Market Prediction," Sustainability, MDPI, vol. 10(10), pages 1-18, October.
    9. Schnaubelt, Matthias, 2022. "Deep reinforcement learning for the optimal placement of cryptocurrency limit orders," European Journal of Operational Research, Elsevier, vol. 296(3), pages 993-1006.
    10. Wenyong Zhang & Lingfei Li & Gongqiu Zhang, 2021. "A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface," Papers 2106.07177, arXiv.org, revised Jan 2022.
    11. Gabriel Borrageiro & Nick Firoozye & Paolo Barucca, 2021. "Online Learning with Radial Basis Function Networks," Papers 2103.08414, arXiv.org, revised Oct 2022.
    12. Gao, Xuefeng & Xu, Tianrun, 2022. "Order scoring, bandit learning and order cancellations," Journal of Economic Dynamics and Control, Elsevier, vol. 134(C).
    13. Ilia Zaznov & Julian Kunkel & Alfonso Dufour & Atta Badii, 2022. "Predicting Stock Price Changes Based on the Limit Order Book: A Survey," Mathematics, MDPI, vol. 10(8), pages 1-33, April.
    14. Luca Grilli & Domenico Santoro, 2022. "Forecasting financial time series with Boltzmann entropy through neural networks," Computational Management Science, Springer, vol. 19(4), pages 665-681, October.
    15. Goodell, John W. & Kumar, Satish & Lim, Weng Marc & Pattnaik, Debidutta, 2021. "Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis," Journal of Behavioral and Experimental Finance, Elsevier, vol. 32(C).
    16. Adamantios Ntakaris & Moncef Gabbouj & Juho Kanniainen, 2023. "Optimum Output Long Short-Term Memory Cell for High-Frequency Trading Forecasting," Papers 2304.09840, arXiv.org, revised May 2023.
    17. Chaeshick Chung & Sukjin Park, 2021. "Deep Learning Market Microstructure: Dual-Stage Attention-Based Recurrent Neural Networks," Working Papers 2108, Nam Duck-Woo Economic Research Institute, Sogang University (Former Research Institute for Market Economy).
    18. Kristof Lommers & Ouns El Harzli & Jack Kim, 2021. "Confronting Machine Learning With Financial Research," Papers 2103.00366, arXiv.org, revised Mar 2021.
    19. Adamantios Ntakaris & Juho Kanniainen & Moncef Gabbouj & Alexandros Iosifidis, 2020. "Mid-price prediction based on machine learning methods with technical and quantitative indicators," PLOS ONE, Public Library of Science, vol. 15(6), pages 1-39, June.
    20. Jie Chen & Lingfei Li, 2021. "Data-driven Hedging of Stock Index Options via Deep Learning," Papers 2111.03477, arXiv.org.

    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:2207.11577. 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.