IDEAS home Printed from https://ideas.repec.org/a/eee/finlet/v89y2026ics1544612325025668.html

Interpretable AI for financial risk perception: A machine learning approach to corporate crisis prediction

Author

Listed:
  • Geng, Xiaoyuan
  • Wang, Haonan
  • Yan, Liangyu

Abstract

Predicting financial crises is important for maintaining stable markets and helping people make smart choices. Machine learning has made better predictions; however, many models are still difficult to understand and use. This study created an easy-to-understand AI method to predict financial crises using an improved LightGBM model. This study uses data on Chinese companies covering 2007 to 2023. This study examined 1293 indicators, such as financial ratios, company reports, and media attention. To fix the data issues, the model used random oversampling and Bayesian tuning. Tests showed that the model worked well, reducing the investment risk by >60 %. They found 15 key predictors, including ROE and market type. The SHAP analysis shows how these factors affect crisis chances, providing clear insights into the risks. This study shows that understandable AI can help investors and managers to see risks better and act early. These findings help to turn complex predictions into clear and useful insights for financial decisions.

Suggested Citation

  • Geng, Xiaoyuan & Wang, Haonan & Yan, Liangyu, 2026. "Interpretable AI for financial risk perception: A machine learning approach to corporate crisis prediction," Finance Research Letters, Elsevier, vol. 89(C).
    • Handle: RePEc:eee:finlet:v:89:y:2026:i:c:s1544612325025668
    DOI: 10.1016/j.frl.2025.109317
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1544612325025668
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.frl.2025.109317?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    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:eee:finlet:v:89:y:2026:i:c:s1544612325025668. 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.

    We have no bibliographic references for this item. You can help adding them by using 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/frl .

    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.