BIROn - Birkbeck Institutional Research Online

    Explainable Machine Learning to predict the cost of capital

    Bußmann, N. and Giudici, P. and Tanda, A. and Yu, Ellen Pei-yi (2025) Explainable Machine Learning to predict the cost of capital. Frontiers in Artificial Intelligence 8 , ISSN 2624-8212.

    [img] Text
    55604.pdf - Published Version of Record
    Available under License Creative Commons Attribution.

    Download (1MB)

    Abstract

    This study investigates through explainable AI the impact of financial and non-financial factors on a firm's ex-ante cost of capital, which is the reflection of investors' perception of a firm's riskiness. We apply the XGBoost algorithm and the Shapley value approach to a sample of more than 1,400 listed companies worldwide. Results indicate the most relevant financial and non-financial indicators are: firm size, ROE, firm portfolio risk, and regulatory quality. These factors influence firm's ex-ante cost of equity by changing its investors' risk perception. We also suggest the relevance of ESG factors in predicting the cost of capital.

    Metadata

    Item Type: Article
    School: Birkbeck Faculties and Schools > Faculty of Business and Law > Birkbeck Business School
    Research Centres and Institutes: Accounting and Finance Research Centre
    Depositing User: Ellen Yu
    Date Deposited: 03 Jun 2025 10:40
    Last Modified: 02 Sep 2025 12:50
    URI: https://eprints.bbk.ac.uk/id/eprint/55604

    Statistics

    Activity Overview
    6 month trend
    14Downloads
    6 month trend
    87Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item
    Edit/View Item