IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2508.02283.html
   My bibliography  Save this paper

An Enhanced Focal Loss Function to Mitigate Class Imbalance in Auto Insurance Fraud Detection with Explainable AI

Author

Listed:
  • Francis Boabang
  • Samuel Asante Gyamerah

Abstract

In insurance fraud prediction, handling class imbalance remains a critical challenge. This paper presents a novel multistage focal loss function designed to enhance the performance of machine learning models in such imbalanced settings by helping to escape local minima and converge to a good solution. Building upon the foundation of the standard focal loss, our proposed approach introduces a dynamic, multi-stage convex and nonconvex mechanism that progressively adjusts the focus on hard-to-classify samples across training epochs. This strategic refinement facilitates more stable learning and improved discrimination between fraudulent and legitimate cases. Through extensive experimentation on a real-world insurance dataset, our method achieved better performance than the traditional focal loss, as measured by accuracy, precision, F1-score, recall and Area Under the Curve (AUC) metrics on the auto insurance dataset. These results demonstrate the efficacy of the multistage focal loss in boosting model robustness and predictive accuracy in highly skewed classification tasks, offering significant implications for fraud detection systems in the insurance industry. An explainable model is included to interpret the results.

Suggested Citation

  • Francis Boabang & Samuel Asante Gyamerah, 2025. "An Enhanced Focal Loss Function to Mitigate Class Imbalance in Auto Insurance Fraud Detection with Explainable AI," Papers 2508.02283, arXiv.org.
  • Handle: RePEc:arx:papers:2508.02283
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2508.02283
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Perez-Castrillo, David & Wettstein, David, 2001. "Bidding for the Surplus : A Non-cooperative Approach to the Shapley Value," Journal of Economic Theory, Elsevier, vol. 100(2), pages 274-294, October.
    2. Surjeet Dalal & Bijeta Seth & Magdalena Radulescu & Carmen Secara & Claudia Tolea, 2022. "Predicting Fraud in Financial Payment Services through Optimized Hyper-Parameter-Tuned XGBoost Model," Mathematics, MDPI, vol. 10(24), pages 1-17, December.
    3. Jörn Debener & Volker Heinke & Johannes Kriebel, 2023. "Detecting insurance fraud using supervised and unsupervised machine learning," Journal of Risk & Insurance, The American Risk and Insurance Association, vol. 90(3), pages 743-768, September.
    4. M. Albizuri & J. Echarri & J. Zarzuelo, 2015. "A non-cooperative mechanism for the Shapley value of airport problems," Annals of Operations Research, Springer, vol. 235(1), pages 1-11, December.
    5. Ding, Ning & Ruan, Xiao & Wang, Hao & Liu, Yuan, 2025. "Automobile Insurance Fraud Detection Based on PSO-XGBoost Model and Interpretable Machine Learning Method," Insurance: Mathematics and Economics, Elsevier, vol. 120(C), pages 51-60.
    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. M. J. Albizuri & J. M. Echarri & J. M. Zarzuelo, 2018. "A Non-cooperative Mechanism Yielding the Nucleolus of Airport Problems," Group Decision and Negotiation, Springer, vol. 27(1), pages 153-163, February.
    2. Wenzhong Li & Genjiu Xu & Rong Zou & Dongshuang Hou, 2022. "The allocation of marginal surplus for cooperative games with transferable utility," International Journal of Game Theory, Springer;Game Theory Society, vol. 51(2), pages 353-377, June.
    3. Jean-François Caulier & Michel Grabisch & Agnieszka Rusinowska, 2015. "An allocation rule for dynamic random network formation processes," Economic Theory, Springer;Society for the Advancement of Economic Theory (SAET), vol. 60(2), pages 283-313, October.
    4. Laruelle, Annick & Valenciano, Federico, 2008. "Noncooperative foundations of bargaining power in committees and the Shapley-Shubik index," Games and Economic Behavior, Elsevier, vol. 63(1), pages 341-353, May.
    5. van den Brink, René & van der Laan, Gerard & Moes, Nigel, 2013. "A strategic implementation of the Average Tree solution for cycle-free graph games," Journal of Economic Theory, Elsevier, vol. 148(6), pages 2737-2748.
    6. Bergantiños, Gustavo & Vidal-Puga, Juan, 2010. "Realizing fair outcomes in minimum cost spanning tree problems through non-cooperative mechanisms," European Journal of Operational Research, Elsevier, vol. 201(3), pages 811-820, March.
    7. Sylvain Béal & Eric Rémila & Philippe Solal, 2017. "Axiomatization and implementation of a class of solidarity values for TU-games," Theory and Decision, Springer, vol. 83(1), pages 61-94, June.
    8. Roberto Serrano, 2007. "Cooperative Games: Core and Shapley Value," Working Papers wp2007_0709, CEMFI.
    9. Michela Chessa & Nobuyuki Hanaki & Aymeric Lardon & Takashi Yamada, 2022. "Cost of complexity in implementing the Shapley value by choosing a proposer through a bidding procedure," ISER Discussion Paper 1176, Institute of Social and Economic Research, The University of Osaka.
    10. Ander Perez-Orive & Andrea Caggese, 2017. "Capital Misallocation and Secular Stagnation," 2017 Meeting Papers 382, Society for Economic Dynamics.
    11. Tapking, Jens, 2006. "Multiple equilibrium overnight rates in a dynamic interbank market game," Games and Economic Behavior, Elsevier, vol. 56(2), pages 350-370, August.
    12. Inés Macho-Stadler & David Pérez-Castrillo & David Wettstein, 2010. "Dividends and weighted values in games with externalities," International Journal of Game Theory, Springer;Game Theory Society, vol. 39(1), pages 177-184, March.
    13. Burguet, Roberto & Caminal, Ramon, 2020. "Coalitional bargaining with consistent counterfactuals," Journal of Economic Theory, Elsevier, vol. 187(C).
    14. Chessa, Michela & Hanaki, Nobuyuki & Lardon, Aymeric & Yamada, Takashi, 2022. "The effect of choosing a proposer through a bidding procedure in implementing the Shapley value," Journal of Economic Psychology, Elsevier, vol. 93(C).
    15. Chessa, Michela & Hanaki, Nobuyuki & Lardon, Aymeric & Yamada, Takashi, 2023. "An experiment on the Nash program: A comparison of two strategic mechanisms implementing the Shapley value," Games and Economic Behavior, Elsevier, vol. 141(C), pages 88-104.
    16. Koji Yokote, 2015. "Weak addition invariance and axiomatization of the weighted Shapley value," International Journal of Game Theory, Springer;Game Theory Society, vol. 44(2), pages 275-293, May.
    17. Yoshio Kamijo, 2013. "The collective value: a new solution for games with coalition structures," TOP: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 21(3), pages 572-589, October.
    18. Yokote, Koji & Kongo, Takumi & Funaki, Yukihiko, 2018. "The balanced contributions property for equal contributors," Games and Economic Behavior, Elsevier, vol. 108(C), pages 113-124.
    19. Vidal-Puga, Juan, 2013. "A non-cooperative approach to the ordinal Shapley rule," MPRA Paper 43790, University Library of Munich, Germany.
    20. Navarro Noemí & Perea Andres, 2013. "A Simple Bargaining Procedure for the Myerson Value," The B.E. Journal of Theoretical Economics, De Gruyter, vol. 13(1), pages 131-150, May.

    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:2508.02283. 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.