IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2606.00060.html

Machine Learning-Based Bitcoin Trading Under Transaction Costs: Evidence From Walk-Forward Forecasting

Author

Listed:
  • Andrei Bysik
  • Robert 'Slepaczuk

Abstract

This paper investigates whether machine learning forecasts of hourly BTC-USDT returns can be converted into economically meaningful trading performance after transaction costs. Using approximately 70,000 hourly observations from 2018-2026, XGBoost, LSTM, and iTransformer are evaluated in a 27-fold walk-forward protocol. All three models produce positive gross trading performance in selected configurations, but naive sign-based strategies fail once transaction costs of ten basis points are imposed. A cost-aware execution filter, which prevents trades only when the forecast magnitude exceeds a transaction-cost-based threshold, sharply reduces turnover and restores profitability in selected configurations. The strongest long-only XGBoost strategy produces annualised returns above 65% with a Sharpe ratio above one. Additional tests show that technical indicators improve performance in selected cases, EGARCH-derived features do not provide uniformly robust gains, and XGBoost is descriptively stronger than the neural alternatives, although bootstrap evidence does not support formal statistical dominance. Loss-function and model-selection effects are secondary and statistically fragile. The results show that the main obstacle in hourly cryptocurrency trading is not only weak predictability, but also the way forecasts are converted into trades.

Suggested Citation

  • Andrei Bysik & Robert 'Slepaczuk, 2026. "Machine Learning-Based Bitcoin Trading Under Transaction Costs: Evidence From Walk-Forward Forecasting," Papers 2606.00060, arXiv.org.
    • Handle: RePEc:arx:papers:2606.00060
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2606.00060
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. 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.
    2. Gil Cohen, 2023. "Intraday algorithmic trading strategies for cryptocurrencies," Review of Quantitative Finance and Accounting, Springer, vol. 61(1), pages 395-409, July.
    3. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," Review of Finance, European Finance Association, vol. 33(5), pages 2223-2273.
    4. Laura Alessandretti & Abeer ElBahrawy & Luca Maria Aiello & Andrea Baronchelli, 2018. "Anticipating cryptocurrency prices using machine learning," Papers 1805.08550, arXiv.org, revised Nov 2018.
    5. Victor DeMiguel & Lorenzo Garlappi & Raman Uppal, 2009. "Optimal Versus Naive Diversification: How Inefficient is the 1-N Portfolio Strategy?," The Review of Financial Studies, Society for Financial Studies, vol. 22(5), pages 1915-1953, May.
    6. Laura Alessandretti & Abeer ElBahrawy & Luca Maria Aiello & Andrea Baronchelli, 2018. "Anticipating Cryptocurrency Prices Using Machine Learning," Complexity, Hindawi, vol. 2018, pages 1-16, November.
    7. Jakub Micha'nk'ow & Pawe{l} Sakowski & Robert 'Slepaczuk, 2024. "Generalized Mean Absolute Directional Loss as a Solution to Overfitting and High Transaction Costs in Machine Learning Models Used in High-Frequency Algorithmic Investment Strategies," Papers 2412.18405, arXiv.org.
    8. Clifford S. Asness & Tobias J. Moskowitz & Lasse Heje Pedersen, 2013. "Value and Momentum Everywhere," Journal of Finance, American Finance Association, vol. 68(3), pages 929-985, June.
    9. Jegadeesh, Narasimhan & Titman, Sheridan, 1993. "Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency," Journal of Finance, American Finance Association, vol. 48(1), pages 65-91, March.
    10. Helder Sebastião & Pedro Godinho, 2021. "Forecasting and trading cryptocurrencies with machine learning under changing market conditions," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 7(1), pages 1-30, December.
    11. Evangelos Liaras & Michail Nerantzidis & Antonios Alexandridis, 2024. "Machine learning in accounting and finance research: a literature review," Review of Quantitative Finance and Accounting, Springer, vol. 63(4), pages 1431-1471, November.
    12. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," The Review of Financial Studies, Society for Financial Studies, vol. 33(5), pages 2223-2273.
    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. 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.
    2. Szymon Lis & Robert 'Slepaczuk & Pawe{l} Sakowski, 2026. "Overreaction as an indicator for momentum in algorithmic trading: A Case of AAPL stocks," Papers 2602.18912, arXiv.org.
    3. Yichen Luo & Yebo Feng & Jiahua Xu & Paolo Tasca & Yang Liu, 2025. "LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management," Papers 2501.00826, arXiv.org, revised Jun 2026.
    4. Bolin Mao & Chenhui Chu & Yuta Nakashima & Hajime Nagahara, 2022. "Efficient Market Hypothesis Test with Stock Tweets and Natural Language Processing Models," KIER Working Papers 1082, Kyoto University, Institute of Economic Research.
    5. Duygu Ider & Stefan Lessmann, 2022. "Forecasting Cryptocurrency Returns from Sentiment Signals: An Analysis of BERT Classifiers and Weak Supervision," Papers 2204.05781, arXiv.org, revised Mar 2023.
    6. Maher Hamid, 2026. "Implementing domain-specific LLMs for strategic investment decisions: a retrospective case study comparing AI and human expertise," Digital Finance, Springer, vol. 8(1), pages 1-134, March.
    7. Rubesam, Alexandre, 2022. "Machine learning portfolios with equal risk contributions: Evidence from the Brazilian market," Emerging Markets Review, Elsevier, vol. 51(PB).
    8. Guillaume Chevalier & Guillaume Coqueret & Thomas Raffinot, 2022. "Supervised portfolios," Post-Print hal-04144588, HAL.
    9. Peter Andre & Philipp Schirmer & Johannes Wohlfart, 2023. "Mental Models of the Stock Market," CESifo Working Paper Series 10691, CESifo.
    10. Chen, Yuzhi & Zhang, Deyuan & Li, Xinyue & Su, Hang, 2026. "Multi-term momentum effect and driving mechanisms based on machine learning," Pacific-Basin Finance Journal, Elsevier, vol. 96(C).
    11. Jing Hao & Feng He & Feng Ma & Shibo Zhang & Xiaotao Zhang, 2025. "Machine learning vs deep learning in stock market investment: an international evidence," Annals of Operations Research, Springer, vol. 348(1), pages 93-115, May.
    12. Cakici, Nusret & Fieberg, Christian & Metko, Daniel & Zaremba, Adam, 2023. "Machine learning goes global: Cross-sectional return predictability in international stock markets," Journal of Economic Dynamics and Control, Elsevier, vol. 155(C).
    13. Tobek, Ondrej & Hronec, Martin, 2021. "Does it pay to follow anomalies research? Machine learning approach with international evidence," Journal of Financial Markets, Elsevier, vol. 56(C).
    14. Baba-Yara, Fahiz & Boons, Martijn & Tamoni, Andrea, 2024. "Persistent and transitory components of firm characteristics: Implications for asset pricing," Journal of Financial Economics, Elsevier, vol. 154(C).
    15. Wang, Nianling & Zhang, Mingzhi & Zhang, Yuan, 2024. "Return prediction: A tree-based conditional sort approach with firm characteristics," Finance Research Letters, Elsevier, vol. 60(C).
    16. Blanco, Ivan & De Jesus, Miguel & Remesal, Alvaro, 2023. "Overlapping momentum portfolios," Journal of Empirical Finance, Elsevier, vol. 72(C), pages 1-22.
    17. Na, Haejung & Kim, Soonho, 2021. "Predicting stock prices based on informed traders’ activities using deep neural networks," Economics Letters, Elsevier, vol. 204(C).
    18. Dong, Mengmeng, 2025. "Economic aggregation of return signals in global markets," Journal of Empirical Finance, Elsevier, vol. 84(C).
    19. Bui, Dien Giau & Kong, De-Rong & Lin, Chih-Yung & Lin, Tse-Chun, 2023. "Momentum in machine learning: Evidence from the Taiwan stock market," Pacific-Basin Finance Journal, Elsevier, vol. 82(C).
    20. Ma, Tian & Sheng, Haoyun & Wang, Yuejie, 2024. "Noisy market, machine learning and fundamental momentum," Pacific-Basin Finance Journal, Elsevier, vol. 86(C).

    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:2606.00060. 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: https://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.