IDEAS home Printed from https://ideas.repec.org/a/gam/jrisks/v10y2022i8p154-d877518.html
   My bibliography  Save this article

Robust Classification via Support Vector Machines

Author

Listed:
  • Alexandru V. Asimit

    (Faculty of Actuarial Science & Insurance, Bayes Business School, City, University of London, 106 Bunhill Row, London EC1Y 8TZ, UK
    These authors contributed equally to this work.)

  • Ioannis Kyriakou

    (Faculty of Actuarial Science & Insurance, Bayes Business School, City, University of London, 106 Bunhill Row, London EC1Y 8TZ, UK
    These authors contributed equally to this work.)

  • Simone Santoni

    (Faculty of Management, Bayes Business School, City, University of London, 106 Bunhill Row, London EC1Y 8TZ, UK
    These authors contributed equally to this work.)

  • Salvatore Scognamiglio

    (Department of Management and Quantitative Sciences, University of Naples Parthenope, Via Generale Parisi 13, 80132 Naples, Italy
    These authors contributed equally to this work.)

  • Rui Zhu

    (Faculty of Actuarial Science & Insurance, Bayes Business School, City, University of London, 106 Bunhill Row, London EC1Y 8TZ, UK
    These authors contributed equally to this work.)

Abstract

Classification models are very sensitive to data uncertainty, and finding robust classifiers that are less sensitive to data uncertainty has raised great interest in the machine learning literature. This paper aims to construct robust support vector machine classifiers under feature data uncertainty via two probabilistic arguments. The first classifier, Single Perturbation , reduces the local effect of data uncertainty with respect to one given feature and acts as a local test that could confirm or refute the presence of significant data uncertainty for that particular feature. The second classifier, Extreme Empirical Loss , aims to reduce the aggregate effect of data uncertainty with respect to all features, which is possible via a trade-off between the number of prediction model violations and the size of these violations. Both methodologies are computationally efficient and our extensive numerical investigation highlights the advantages and possible limitations of the two robust classifiers on synthetic and real-life insurance claims and mortgage lending data, but also the fairness of an automatized decision based on our classifier.

Suggested Citation

  • Alexandru V. Asimit & Ioannis Kyriakou & Simone Santoni & Salvatore Scognamiglio & Rui Zhu, 2022. "Robust Classification via Support Vector Machines," Risks, MDPI, vol. 10(8), pages 1-25, August.
  • Handle: RePEc:gam:jrisks:v:10:y:2022:i:8:p:154-:d:877518
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-9091/10/8/154/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-9091/10/8/154/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Steenackers, A. & Goovaerts, M. J., 1989. "A credit scoring model for personal loans," Insurance: Mathematics and Economics, Elsevier, vol. 8(1), pages 31-34, March.
    2. Olivier Ledoit & Michael Wolf, 2019. "The power of (non-)linear shrinking: a review and guide to covariance matrix estimation," ECON - Working Papers 323, Department of Economics - University of Zurich, revised Feb 2020.
    3. Michael D. Eriksen & James B. Kau & Donald C. Keenan, 2013. "The Impact of Second Loans on Subprime Mortgage Defaults," Real Estate Economics, American Real Estate and Urban Economics Association, vol. 41(4), pages 858-886, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Gian Paolo Clemente & Francesco Della Corte & Nino Savelli & Diego Zappa, 2023. "Special Issue “Data Science in Insurance”," Risks, MDPI, vol. 11(5), pages 1-3, April.

    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. Stefano Colonnello & Mariela Dal Borgo, 2024. "Raising Household Leverage: Evidence from Co-Financed Mortgages," Working Papers 2024: 01, Department of Economics, University of Venice "Ca' Foscari".
    2. B Baesens & T Van Gestel & S Viaene & M Stepanova & J Suykens & J Vanthienen, 2003. "Benchmarking state-of-the-art classification algorithms for credit scoring," Journal of the Operational Research Society, Palgrave Macmillan;The OR Society, vol. 54(6), pages 627-635, June.
    3. A?da Kammoun & Imen Triki, 2016. "Credit Scoring Models for a Tunisian Microfinance Institution: Comparison between Artificial Neural Network and Logistic Regression," Review of Economics & Finance, Better Advances Press, Canada, vol. 6, pages 61-78, February.
    4. Tsukahara, Fábio Yasuhiro & Kimura, Herbert & Sobreiro, Vinicius Amorim & Zambrano, Juan Carlos Arismendi, 2016. "Validation of default probability models: A stress testing approach," International Review of Financial Analysis, Elsevier, vol. 47(C), pages 70-85.
    5. Damir Filipovic & Paul Schneider, 2024. "Fundamental properties of linear factor models," Papers 2409.02521, arXiv.org, revised Oct 2024.
    6. Pier Francesco Procacci & Tomaso Aste, 2021. "Portfolio Optimization with Sparse Multivariate Modelling," Papers 2103.15232, arXiv.org.
    7. Andrey Filchenkov & Natalia Khanzhina & Arina Tsai & Ivan Smetannikov, 2021. "Regularization of Autoencoders for Bank Client Profiling Based on Financial Transactions," Risks, MDPI, vol. 9(3), pages 1-16, March.
    8. Agustin Pérez-Martín & Agustin Pérez-Torregrosa & Alejandro Rabasa & Marta Vaca, 2020. "Feature Selection to Optimize Credit Banking Risk Evaluation Decisions for the Example of Home Equity Loans," Mathematics, MDPI, vol. 8(11), pages 1-16, November.
    9. Azam, Rehan & Muhammad, Danish & Syed Akbar, Suleman, 2012. "The significance of socioeconomic factors on personal loan decision a study of consumer banking local private banks in Pakistan," MPRA Paper 42322, University Library of Munich, Germany.
    10. Mestiri, Sami & Farhat, Abdejelil, 2018. "Credit Risk Prediction based on Bayesian estimation of logistic regression model with random effects," MPRA Paper 119960, University Library of Munich, Germany.
    11. Hussein A. Abdou & John Pointon, 2011. "Credit Scoring, Statistical Techniques And Evaluation Criteria: A Review Of The Literature," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 18(2-3), pages 59-88, April.
    12. Taras Bodnar & Nestor Parolya & Erik Thors'en, 2022. "Two is better than one: Regularized shrinkage of large minimum variance portfolio," Papers 2202.06666, arXiv.org.
    13. Adriana Uquillas, 2017. "Determinantes del riesgo comportamental en préstamos de consumo y microcrédito: Un estudio de caso en Centro América," Revista de Investigación en Ciencias Contables y Administrativas, Universidad Michoacana de San Nicolás de Hidalgo, Facultad de Contaduría y Ciencias Administrativas, vol. 3(1), pages 35-66, July.
    14. Elena Ivona DUMITRESCU & Sullivan HUE & Christophe HURLIN & Sessi TOKPAVI, 2020. "Machine Learning or Econometrics for Credit Scoring: Let’s Get the Best of Both Worlds," LEO Working Papers / DR LEO 2839, Orleans Economics Laboratory / Laboratoire d'Economie d'Orleans (LEO), University of Orleans.
    15. Andrew Grant & Oh Kang Kwon & Steve Satchell, 2024. "Properties of risk aversion estimated from portfolio weights," Journal of Asset Management, Palgrave Macmillan, vol. 25(5), pages 427-444, September.
    16. Jianhua Jiang & Xianqiu Meng & Yang Liu & Huan Wang, 2022. "An Enhanced TSA-MLP Model for Identifying Credit Default Problems," SAGE Open, , vol. 12(2), pages 21582440221, April.
    17. Bart Baesens & Rudy Setiono & Christophe Mues & Jan Vanthienen, 2003. "Using Neural Network Rule Extraction and Decision Tables for Credit-Risk Evaluation," Management Science, INFORMS, vol. 49(3), pages 312-329, March.
    18. Aida Krichene Abdelmoula, 2015. "Bank Credit Risk Analysis with K-Nearest-Neighbor Classifier: Case of Tunisian Banks," Journal of Accounting and Management Information Systems, Faculty of Accounting and Management Information Systems, The Bucharest University of Economic Studies, vol. 14(1), pages 79-106, March.
    19. Rebeca Peláez & Ricardo Cao & Juan M. Vilar, 2022. "Bootstrap Bandwidth Selection and Confidence Regions for Double Smoothed Default Probability Estimation," Mathematics, MDPI, vol. 10(9), pages 1-25, May.
    20. Maria Rocha Sousa & João Gama & Elísio Brandão, 2013. "Introducing time-changing economics into credit scoring," FEP Working Papers 513, Universidade do Porto, Faculdade de Economia do Porto.

    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:gam:jrisks:v:10:y:2022:i:8:p:154-:d:877518. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.