IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2505.16136.html
   My bibliography  Save this paper

Interpretable Machine Learning for Macro Alpha: A News Sentiment Case Study

Author

Listed:
  • Yuke Zhang

Abstract

This study introduces an interpretable machine learning (ML) framework to extract macroeconomic alpha from global news sentiment. We process the Global Database of Events, Language, and Tone (GDELT) Project's worldwide news feed using FinBERT -- a Bidirectional Encoder Representations from Transformers (BERT) based model pretrained on finance-specific language -- to construct daily sentiment indices incorporating mean tone, dispersion, and event impact. These indices drive an XGBoost classifier, benchmarked against logistic regression, to predict next-day returns for EUR/USD, USD/JPY, and 10-year U.S. Treasury futures (ZN). Rigorous out-of-sample (OOS) backtesting (5-fold expanding-window cross-validation, OOS period: c. 2017-April 2025) demonstrates exceptional, cost-adjusted performance for the XGBoost strategy: Sharpe ratios achieve 5.87 (EUR/USD), 4.65 (USD/JPY), and 4.65 (Treasuries), with respective compound annual growth rates (CAGRs) exceeding 50% in Foreign Exchange (FX) and 22% in bonds. Shapley Additive Explanations (SHAP) affirm that sentiment dispersion and article impact are key predictive features. Our findings establish that integrating domain-specific Natural Language Processing (NLP) with interpretable ML offers a potent and explainable source of macro alpha.

Suggested Citation

  • Yuke Zhang, 2025. "Interpretable Machine Learning for Macro Alpha: A News Sentiment Case Study," Papers 2505.16136, arXiv.org.
  • Handle: RePEc:arx:papers:2505.16136
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2505.16136
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Paul C. Tetlock, 2007. "Giving Content to Investor Sentiment: The Role of Media in the Stock Market," Journal of Finance, American Finance Association, vol. 62(3), pages 1139-1168, June.
    2. Diego García, 2013. "Sentiment during Recessions," Journal of Finance, American Finance Association, vol. 68(3), pages 1267-1300, June.
    3. Tim Loughran & Bill Mcdonald, 2011. "When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10‐Ks," Journal of Finance, American Finance Association, vol. 66(1), pages 35-65, February.
    4. Pekka Malo & Ankur Sinha & Pekka Korhonen & Jyrki Wallenius & Pyry Takala, 2014. "Good debt or bad debt: Detecting semantic orientations in economic texts," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 65(4), pages 782-796, April.
    5. Joseph E. Engelberg & Christopher A. Parsons, 2011. "The Causal Impact of Media in Financial Markets," Journal of Finance, American Finance Association, vol. 66(1), pages 67-97, February.
    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. Kirtac, Kemal & Germano, Guido, 2024. "Sentiment trading with large language models," Finance Research Letters, Elsevier, vol. 62(PB).
    2. Ahmed, Yousry & Elshandidy, Tamer, 2016. "The effect of bidder conservatism on M&A decisions: Text-based evidence from US 10-K filings," International Review of Financial Analysis, Elsevier, vol. 46(C), pages 176-190.
    3. Ahmad, Khurshid & Han, JingGuang & Hutson, Elaine & Kearney, Colm & Liu, Sha, 2016. "Media-expressed negative tone and firm-level stock returns," Journal of Corporate Finance, Elsevier, vol. 37(C), pages 152-172.
    4. Vegard Høghaug Larsen & Leif Anders Thorsrud, 2022. "Asset returns, news topics, and media effects," Scandinavian Journal of Economics, Wiley Blackwell, vol. 124(3), pages 838-868, July.
    5. Saadon, Yossi & Schreiber, Ben Z., 2023. "Newspapers tone and the overnight-intraday stock return anomaly," Journal of Financial Markets, Elsevier, vol. 65(C).
    6. Chau, Michael & Lin, Chih-Yung & Lin, Tse-Chun, 2020. "Wisdom of crowds before the 2007–2009 global financial crisis," Journal of Financial Stability, Elsevier, vol. 48(C).
    7. Chouliaras, Andreas, 2016. "The Effect of Infomation on Financial Markets: A Survey," MPRA Paper 71396, University Library of Munich, Germany.
    8. Goldman, Eitan & Gupta, Nandini & Israelsen, Ryan, 2024. "Political polarization in financial news," Journal of Financial Economics, Elsevier, vol. 155(C).
    9. Tom Marty & Bruce Vanstone & Tobias Hahn, 2020. "News media analytics in finance: a survey," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 60(2), pages 1385-1434, June.
    10. Carlini, Federico & Cucinelli, Doriana & Previtali, Daniele & Soana, Maria Gaia, 2020. "Don't talk too bad! stock market reactions to bank corporate governance news," Journal of Banking & Finance, Elsevier, vol. 121(C).
    11. Emanuele Bajo & Marco Bigelli & Carlo Raimondo, 2020. "Ownership ties, conflict of interest, and the tone of news," European Financial Management, European Financial Management Association, vol. 26(3), pages 560-578, June.
    12. Liu, Sha & Han, Jingguang, 2020. "Media tone and expected stock returns," International Review of Financial Analysis, Elsevier, vol. 70(C).
    13. John Griffith & Mohammad Najand & Jiancheng Shen, 2020. "Emotions in the Stock Market," Journal of Behavioral Finance, Taylor & Francis Journals, vol. 21(1), pages 42-56, January.
    14. Narayan, Paresh Kumar & Bannigidadmath, Deepa, 2017. "Does Financial News Predict Stock Returns? New Evidence from Islamic and Non-Islamic Stocks," Pacific-Basin Finance Journal, Elsevier, vol. 42(C), pages 24-45.
    15. Nicky J. Ferguson & Dennis Philip & Herbert Y. T. Lam & Jie Michael Guo, 2015. "Media Content and Stock Returns: The Predictive Power of Press," Multinational Finance Journal, Multinational Finance Journal, vol. 19(1), pages 1-31, March.
    16. Luiz Renato Lima & Lucas Lúcio Godeiro & Mohammed Mohsin, 2021. "Time-Varying Dictionary and the Predictive Power of FED Minutes," Computational Economics, Springer;Society for Computational Economics, vol. 57(1), pages 149-181, January.
    17. Bajo, Emanuele & Raimondo, Carlo, 2017. "Media sentiment and IPO underpricing," Journal of Corporate Finance, Elsevier, vol. 46(C), pages 139-153.
    18. Giannetti, Mariassunta & Braggion, Fabio, 2013. "Public Debate and Stock Prices: Evidence from the Voting Premium," CEPR Discussion Papers 9619, C.E.P.R. Discussion Papers.
    19. Yan Luo & Linying Zhou, 2020. "Textual tone in corporate financial disclosures: a survey of the literature," International Journal of Disclosure and Governance, Palgrave Macmillan, vol. 17(2), pages 101-110, September.
    20. Bennani, Hamza, 2018. "Media coverage and ECB policy-making: Evidence from an augmented Taylor rule," Journal of Macroeconomics, Elsevier, vol. 57(C), pages 26-38.

    More about this item

    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:2505.16136. 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.