IDEAS home Printed from https://ideas.repec.org/a/gam/jjrfmx/v18y2025i7p348-d1685755.html
   My bibliography  Save this article

Implementing Custom Loss Functions in Advanced Machine Learning Structures for Targeted Outcomes

Author

Listed:
  • Thomas Hitchen

    (Department of Mathematics, University of Manchester, Manchester M13 9PL, UK)

  • Saralees Nadarajah

    (Department of Mathematics, University of Manchester, Manchester M13 9PL, UK)

Abstract

In the era of rapid technological advancement and ever-increasing data availability, the field of risk modeling faces both unprecedented challenges and opportunities. Traditional risk modeling approaches, while robust, often struggle to capture the complexity and dynamic nature of modern risk factors. This paper aims to provide a method for dealing with the insurance pricing problem of pricing predictability and MLOT (Money Left On Table) when writing a book of risks. It also gives an example of how to improve risk selection through suitable choices of machine learning algorithm and acquainted loss function. We apply this methodology to the provided data and discuss the impacts on risk selection and predictive power of the models using the data provided.

Suggested Citation

  • Thomas Hitchen & Saralees Nadarajah, 2025. "Implementing Custom Loss Functions in Advanced Machine Learning Structures for Targeted Outcomes," JRFM, MDPI, vol. 18(7), pages 1-19, June.
    • Handle: RePEc:gam:jjrfmx:v:18:y:2025:i:7:p:348-:d:1685755
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1911-8074/18/7/348/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1911-8074/18/7/348/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Ronald Richman & Mario V. Wüthrich, 2023. "LocalGLMnet: interpretable deep learning for tabular data," Scandinavian Actuarial Journal, Taylor & Francis Journals, vol. 2023(1), pages 71-95, January.
    2. Michel Denuit & Julien Trufin, 2017. "Beyond the Tweedie Reserving Model: The Collective Approach to Loss Development," North American Actuarial Journal, Taylor & Francis Journals, vol. 21(4), pages 611-619, October.
    3. Alma Cohen & Peter Siegelman, 2010. "Testing for Adverse Selection in Insurance Markets," Journal of Risk & Insurance, The American Risk and Insurance Association, vol. 77(1), pages 39-84, March.
    4. Denuit, Michel & Trufin, Julien, 2017. "Beyond the Tweedie Reserving Model: The Collective Approach to Loss Development," LIDAM Reprints ISBA 2017038, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    5. Carina Clemente & Gracinda R. Guerreiro & Jorge M. Bravo, 2023. "Modelling Motor Insurance Claim Frequency and Severity Using Gradient Boosting," Risks, MDPI, vol. 11(9), pages 1-20, September.
    6. Alinta Ann Wilson & Antonio Nehme & Alisha Dhyani & Khaled Mahbub, 2024. "A Comparison of Generalised Linear Modelling with Machine Learning Approaches for Predicting Loss Cost in Motor Insurance," Risks, MDPI, vol. 12(4), pages 1-29, March.
    7. Alina Kulustayeva & Aigul Jondelbayeva & Azhar Nurmagambetova & Aliya Dossayeva & Aliya Bikteubayeva, 2020. "Financial data reporting analysis of the factors influencing on profitability for insurance companies," Entrepreneurship and Sustainability Issues, VsI Entrepreneurship and Sustainability Center, vol. 7(3), pages 2394-2406, March.
    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. Yanez, Juan Sebastian & Pigeon, Mathieu, 2021. "Micro-level parametric duration-frequency-severity modeling for outstanding claim payments," Insurance: Mathematics and Economics, Elsevier, vol. 98(C), pages 106-119.
    2. Crevecoeur, Jonas & Robben, Jens & Antonio, Katrien, 2022. "A hierarchical reserving model for reported non-life insurance claims," Insurance: Mathematics and Economics, Elsevier, vol. 104(C), pages 158-184.
    3. Gadir Alomair, 2024. "Predictive performance of count regression models versus machine learning techniques: A comparative analysis using an automobile insurance claims frequency dataset," PLOS ONE, Public Library of Science, vol. 19(12), pages 1-12, December.
    4. N. Miklós Arató & László Martinek, 2022. "The Quality of Reserve Risk Calculation Models under Solvency II and IFRS 17," Risks, MDPI, vol. 10(11), pages 1-13, October.
    5. Franziska Tausch & Jan Potters & Arno Riedl, 2014. "An experimental investigation of risk sharing and adverse selection," Journal of Risk and Uncertainty, Springer, vol. 48(2), pages 167-186, April.
    6. Gan, Li & Huang, Feng & Mayer, Adalbert, 2015. "A simple test for private information in insurance markets with heterogeneous insurance demand," Economics Letters, Elsevier, vol. 136(C), pages 197-200.
    7. Renuka Sane & Susan Thomas, 2020. "From Participation To Repurchase: Low Income Households And Micro‐insurance," Journal of Risk & Insurance, The American Risk and Insurance Association, vol. 87(3), pages 783-814, September.
    8. Joachim Ragnitz & Marcel Thum, 2013. "Pflichtversicherung gegen Flutschäden?," ifo Dresden berichtet, ifo Institute - Leibniz Institute for Economic Research at the University of Munich, vol. 20(05), pages 33-35, October.
    9. Shi-jie Jiang & Feiyun Xiang & Iris Yang, 2023. "Effect of Prevention Focus on the Relationships Among Driving Accident History, Risk Perception, and Consumers’ Automobile Insurance Coverage Decisions," SAGE Open, , vol. 13(3), pages 21582440231, July.
    10. Sebastian Panthöfer, 2016. "Risk Selection under Public Health Insurance with Opt‐Out," Health Economics, John Wiley & Sons, Ltd., vol. 25(9), pages 1163-1181, September.
    11. Cannon, Edmund & Tonks, Ian, 2016. "Cohort mortality risk or adverse selection in annuity markets?," Journal of Public Economics, Elsevier, vol. 141(C), pages 68-81.
    12. de Meza, David & Webb, David C., 2017. "False diagnoses: pitfalls of testing for asymmetric information in insurance markets," LSE Research Online Documents on Economics 65744, London School of Economics and Political Science, LSE Library.
    13. Manuel Leiria & Nelson Matos & Efigénio Rebelo, 2021. "Non-life insurance cancellation: a systematic quantitative literature review," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 46(4), pages 593-613, October.
    14. Nathaniel Hendren & Camille Landais & Johannes Spinnewijn, 2021. "Choice in Insurance Markets: A Pigouvian Approach to Social Insurance Design," Annual Review of Economics, Annual Reviews, vol. 13(1), pages 457-486, August.
    15. repec:mea:meawpa:12259 is not listed on IDEAS
    16. Ronald Richman & Salvatore Scognamiglio & Mario V. Wuthrich, 2024. "The Credibility Transformer," Papers 2409.16653, arXiv.org.
    17. Wu, Anqi & Zheng, Xiaoting, 2022. "Assortative matching and commercial insurance participation: Evidence from the China Household Finance Survey," Journal of Asian Economics, Elsevier, vol. 80(C).
    18. Robert M. Bushman & Christopher D. Williams & Regina Wittenberg‐Moerman, 2017. "The Informational Role of the Media in Private Lending," Journal of Accounting Research, John Wiley & Sons, Ltd., vol. 55(1), pages 115-152, March.
    19. Kakuho Furukawa & Hibiki Ichiue & Noriyuki Shiraki, 2020. "How Does Climate Change Interact with the Financial System? A Survey," Bank of Japan Working Paper Series 20-E-8, Bank of Japan.
    20. Annan, Francis, 2020. "Does bundling induce adverse selection in insurance?," Economics Letters, Elsevier, vol. 196(C).
    21. Spindler, Martin, 2015. "Asymmetric information in (private) accident insurance," Economics Letters, Elsevier, vol. 130(C), pages 85-88.

    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:gam:jjrfmx:v:18:y:2025:i:7:p:348-:d:1685755. 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.