IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2506.19789.html
   My bibliography  Save this paper

A comparative analysis of machine learning algorithms for predicting probabilities of default

Author

Listed:
  • Adrian Iulian Cristescu
  • Matteo Giordano

Abstract

Predicting the probability of default (PD) of prospective loans is a critical objective for financial institutions. In recent years, machine learning (ML) algorithms have achieved remarkable success across a wide variety of prediction tasks; yet, they remain relatively underutilised in credit risk analysis. This paper highlights the opportunities that ML algorithms offer to this field by comparing the performance of five predictive models-Random Forests, Decision Trees, XGBoost, Gradient Boosting and AdaBoost-to the predominantly used logistic regression, over a benchmark dataset from Scheule et al. (Credit Risk Analytics: The R Companion). Our findings underscore the strengths and weaknesses of each method, providing valuable insights into the most effective ML algorithms for PD prediction in the context of loan portfolios.

Suggested Citation

  • Adrian Iulian Cristescu & Matteo Giordano, 2025. "A comparative analysis of machine learning algorithms for predicting probabilities of default," Papers 2506.19789, arXiv.org.
    • Handle: RePEc:arx:papers:2506.19789
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2506.19789
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Patrick Weber & K. Valerie Carl & Oliver Hinz, 2024. "Applications of Explainable Artificial Intelligence in Finance—a systematic review of Finance, Information Systems, and Computer Science literature," Management Review Quarterly, Springer, vol. 74(2), pages 867-907, June.
    2. Jomark Pablo Noriega & Luis Antonio Rivera & José Alfredo Herrera, 2023. "Machine Learning for Credit Risk Prediction: A Systematic Literature Review," Data, MDPI, vol. 8(11), pages 1-17, November.
    3. Xin Wang & Kai Zong & Cuicui Luo, 2022. "Credit risk detection based on machine learning algorithms," International Journal of Financial Services Management, Inderscience Enterprises Ltd, vol. 11(3), pages 183-189.
    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. Brian Daniel Bernhardt & Chiara Marciano & Mario Rosario Guarracino, 2025. "The Impact of Alternative Data on Default Probability: Analyzing the Italian E-commerce Sector with NLP and Network Structures," SN Operations Research Forum, Springer, vol. 6(2), pages 1-30, June.
    2. Garnik Arakelyan & Armen Ghazaryan, 2025. "Application of a Machine Learning Algorithm to Assess and Minimize Credit Risks," JRFM, MDPI, vol. 18(9), pages 1-16, September.
    3. Nartey Menzo, Benjamin Prince & Mogre, Diana & Asuamah Yeboah, Samuel, 2024. "Beyond Income: The Complexities of Credit Risk in Developing Countries," MPRA Paper 122364, University Library of Munich, Germany, revised 20 Sep 2024.
    4. Tabachová, Zlata & Diem, Christian & Borsos, András & Burger, Csaba & Thurner, Stefan, 2024. "Estimating the impact of supply chain network contagion on financial stability," Journal of Financial Stability, Elsevier, vol. 75(C).
    5. Rogojan Luana Cristina & Croicu Andreea Elena & Iancu Laura Andreea, 2023. "Modern Approaches in Credit Risk Modeling: A Literature Review," Proceedings of the International Conference on Business Excellence, Sciendo, vol. 17(1), pages 1617-1627, July.
    6. Lyne Imene Souadda & Ahmed Rami Halitim & Billel Benilles & José Manuel Oliveira & Patrícia Ramos, 2025. "Optimizing Credit Risk Prediction for Peer-to-Peer Lending Using Machine Learning," Forecasting, MDPI, vol. 7(3), pages 1-31, June.
    7. Tanja Verster & Erika Fourie, 2023. "The Changing Landscape of Financial Credit Risk Models," IJFS, MDPI, vol. 11(3), pages 1-15, August.
    8. Jörn Block & Leif Brändle & Peter Limbach & Tobias Röth & Christopher Albert Sabel, 2025. "Half dead or more alive than ever? New, old, and (increasingly) redundant literature review formats," Management Review Quarterly, Springer, vol. 75(2), pages 993-1008, June.
    9. Mark Potanin & Andrey Chertok & Konstantin Zorin & Cyril Shtabtsovsky, 2023. "Startup success prediction and VC portfolio simulation using CrunchBase data," Papers 2309.15552, arXiv.org.
    10. Xue Wen Tan & Stanley Kok, 2024. "Explainable Risk Classification in Financial Reports," Papers 2405.01881, arXiv.org, revised Dec 2024.
    11. Sahab Zandi & Kamesh Korangi & Mar'ia 'Oskarsd'ottir & Christophe Mues & Cristi'an Bravo, 2024. "Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction," Papers 2402.00299, arXiv.org, revised Jun 2024.
    12. Xue Wen Tan & Stanley Kok, 2025. "Explainable AI for Comprehensive Risk Assessment for Financial Reports: A Lightweight Hierarchical Transformer Network Approach," Papers 2506.23767, arXiv.org, revised Jul 2025.
    13. Jacopo Giacomelli, 2025. "AI-Powered Reduced-Form Model for Default Rate Forecasting," Risks, MDPI, vol. 13(8), pages 1-20, August.
    14. Konstantinos Kofidis & Cătălina Lucia Cocianu, 2024. "Comparative analysis of RF, SVR with Gaussian kernel and LSTM for predicting loan defaults," Journal of Financial Studies, Institute of Financial Studies, vol. 9(17), pages 91-106, November.
    15. Anton van Dyk & Gary van Vuuren, 2023. "Measurement and Calibration of Regulatory Credit Risk Asset Correlations," JRFM, MDPI, vol. 16(9), pages 1-19, September.
    16. Kun Yang & Nikhil Krishnan & Sanjeev R. Kulkarni, 2025. "Financial Data Analysis with Robust Federated Logistic Regression," Papers 2504.20250, arXiv.org.
    17. Brygała Magdalena & Korol Tomasz, 2024. "Personal bankruptcy prediction using machine learning techniques," Economics and Business Review, Sciendo, vol. 10(2), pages 118-142.
    18. Pei, Youquan & Peng, Heng & Xu, Jinfeng, 2024. "A latent class Cox model for heterogeneous time-to-event data," Journal of Econometrics, Elsevier, vol. 239(2).
    19. Flavio Bazzana & Marco Bee & Ahmed Almustfa Hussin Adam Khatir, 2024. "Machine learning techniques for default prediction: an application to small Italian companies," Risk Management, Palgrave Macmillan, vol. 26(1), pages 1-23, February.
    20. Sukru Selim Calik & Andac Akyuz & Zeynep Hilal Kilimci & Kerem Colak, 2025. "Explainable-AI powered stock price prediction using time series transformers: A Case Study on BIST100," Papers 2506.06345, arXiv.org.

    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:2506.19789. 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.