IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2303.16158.html
   My bibliography  Save this paper

Behavioral Machine Learning? Computer Predictions of Corporate Earnings also Overreact

Author

Listed:
  • Murray Z. Frank
  • Jing Gao
  • Keer Yang

Abstract

Machine learning algorithms are known to outperform human analysts in predicting corporate earnings, leading to their rapid adoption. However, we show that leading methods (XGBoost, neural nets, ChatGPT) systematically overreact to news. The overreaction is primarily due to biases in the training data and we show that it cannot be eliminated without compromising accuracy. Analysts with machine learning training overreact much less than do traditional analysts. We provide a model showing that there is a tradeoff between predictive power and rational behavior. Our findings suggest that AI tools reduce but do not eliminate behavioral biases in financial markets.

Suggested Citation

  • Murray Z. Frank & Jing Gao & Keer Yang, 2023. "Behavioral Machine Learning? Computer Predictions of Corporate Earnings also Overreact," Papers 2303.16158, arXiv.org, revised Mar 2025.
    • Handle: RePEc:arx:papers:2303.16158
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2303.16158
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Sean Cao & Wei Jiang & Junbo L. Wang & Baozhong Yang, 2021. "From Man vs. Machine to Man + Machine: The Art and AI of Stock Analyses," NBER Working Papers 28800, National Bureau of Economic Research, Inc.
    2. Qi Chen & Itay Goldstein & Wei Jiang, 2007. "Price Informativeness and Investment Sensitivity to Stock Price," The Review of Financial Studies, Society for Financial Studies, vol. 20(3), pages 619-650.
    3. Begenau, Juliane & Farboodi, Maryam & Veldkamp, Laura, 2018. "Big data in finance and the growth of large firms," Journal of Monetary Economics, Elsevier, vol. 97(C), pages 71-87.
    4. Fama, Eugene F & MacBeth, James D, 1973. "Risk, Return, and Equilibrium: Empirical Tests," Journal of Political Economy, University of Chicago Press, vol. 81(3), pages 607-636, May-June.
    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. Keming Li, 2021. "The effect of option trading," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 7(1), pages 1-32, December.
    2. Liu, Siqi & Yin, Chao & Zeng, Yeqin, 2021. "Abnormal investment and firm performance," International Review of Financial Analysis, Elsevier, vol. 78(C).
    3. Li, Frank Weikai & Sun, Chengzhu, 2022. "Information acquisition and expected returns: Evidence from EDGAR search traffic," Journal of Economic Dynamics and Control, Elsevier, vol. 141(C).
    4. Thierry Foucault & Laurent Frésard, 2012. "Cross-Listing, Investment Sensitivity to Stock Price, and the Learning Hypothesis," The Review of Financial Studies, Society for Financial Studies, vol. 25(11), pages 3305-3350.
    5. Itay Goldstein, 2023. "Information in Financial Markets and Its Real Effects," Review of Finance, European Finance Association, vol. 27(1), pages 1-32.
    6. Jennifer N. Carpenter & Fangzhou Lu & Robert F. Whitelaw, 2015. "The Real Value of China's Stock Market," NBER Working Papers 20957, National Bureau of Economic Research, Inc.
    7. Kusnadi, Yuanto, 2015. "Cross-listings and corporate cash savings: International evidence," Journal of Corporate Finance, Elsevier, vol. 32(C), pages 91-107.
    8. Sun, Chuanping, 2024. "Factor correlation and the cross section of asset returns: A correlation-robust machine learning approach," Journal of Empirical Finance, Elsevier, vol. 77(C).
    9. Yan, Yuxing & Zhang, Shaojun, 2014. "Quality of PIN estimates and the PIN-return relationship," Journal of Banking & Finance, Elsevier, vol. 43(C), pages 137-149.
    10. Andrei, Daniel & Mann, William & Moyen, Nathalie, 2019. "Why did the q theory of investment start working?," Journal of Financial Economics, Elsevier, vol. 133(2), pages 251-272.
    11. Chan, Konan & Li, Fengfei & Lin, Ji-Chai & Lin, Tse-Chun, 2017. "What do stock price levels tell us about the firms?," Journal of Corporate Finance, Elsevier, vol. 46(C), pages 34-50.
    12. Carpenter, Jennifer N. & Lu, Fangzhou & Whitelaw, Robert F., 2018. "The real value of China's stock market," BOFIT Discussion Papers 2/2018, Bank of Finland Institute for Emerging Economies (BOFIT).
    13. Michael J. Brennan & Sahn-Wook Huh & Avanidhar Subrahmanyam, 2016. "Asymmetric Effects of Informed Trading on the Cost of Equity Capital," Management Science, INFORMS, vol. 62(9), pages 2460-2480, September.
    14. Kusnadi, Yuanto & Srinidhi, Bin, 2020. "Cross-country differences in the effect of political connections on stock price informativeness," Journal of Contemporary Accounting and Economics, Elsevier, vol. 16(2).
    15. Ben-Nasr, Hamdi & Alshwer, Abdullah A., 2016. "Does stock price informativeness affect labor investment efficiency?," Journal of Corporate Finance, Elsevier, vol. 38(C), pages 249-271.
    16. Hooy, Chee-Wooi & Lim, Kian-Ping, 2013. "Is market integration associated with informational efficiency of stock markets?," Journal of Policy Modeling, Elsevier, vol. 35(1), pages 29-44.
    17. repec:zbw:bofitp:2018_002 is not listed on IDEAS
    18. Jody Grewal & Clarissa Hauptmann & George Serafeim, 2021. "Material Sustainability Information and Stock Price Informativeness," Journal of Business Ethics, Springer, vol. 171(3), pages 513-544, July.
    19. Pereira da Silva, Paulo, 2021. "Do managers pay attention to the market? A review of the relationship between stock price informativeness and investment," Journal of Multinational Financial Management, Elsevier, vol. 59(C).
    20. Autore, Don M. & Hutton, Irena & Jiang, Danling & Outlaw, Dominque G., 2018. "Short interest as a signal to issue equity," Journal of Corporate Finance, Elsevier, vol. 48(C), pages 797-815.
    21. Pungaliya, Raunaq S. & Wang, Yanbo, 2023. "Machine invasion: Automation in information acquisition and the cross-section of stock returns," Journal of Financial Markets, Elsevier, vol. 64(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:2303.16158. 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.