IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2403.06482.html
   My bibliography  Save this paper

Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning

Author

Listed:
  • Daixin Wang
  • Zhiqiang Zhang
  • Yeyu Zhao
  • Kai Huang
  • Yulin Kang
  • Jun Zhou

Abstract

User financial default prediction plays a critical role in credit risk forecasting and management. It aims at predicting the probability that the user will fail to make the repayments in the future. Previous methods mainly extract a set of user individual features regarding his own profiles and behaviors and build a binary-classification model to make default predictions. However, these methods cannot get satisfied results, especially for users with limited information. Although recent efforts suggest that default prediction can be improved by social relations, they fail to capture the higher-order topology structure at the level of small subgraph patterns. In this paper, we fill in this gap by proposing a motif-preserving Graph Neural Network with curriculum learning (MotifGNN) to jointly learn the lower-order structures from the original graph and higherorder structures from multi-view motif-based graphs for financial default prediction. Specifically, to solve the problem of weak connectivity in motif-based graphs, we design the motif-based gating mechanism. It utilizes the information learned from the original graph with good connectivity to strengthen the learning of the higher-order structure. And considering that the motif patterns of different samples are highly unbalanced, we propose a curriculum learning mechanism on the whole learning process to more focus on the samples with uncommon motif distributions. Extensive experiments on one public dataset and two industrial datasets all demonstrate the effectiveness of our proposed method.

Suggested Citation

  • Daixin Wang & Zhiqiang Zhang & Yeyu Zhao & Kai Huang & Yulin Kang & Jun Zhou, 2024. "Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning," Papers 2403.06482, arXiv.org.
  • Handle: RePEc:arx:papers:2403.06482
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2403.06482
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Viaene, Stijn & Ayuso, Mercedes & Guillen, Montserrat & Van Gheel, Dirk & Dedene, Guido, 2007. "Strategies for detecting fraudulent claims in the automobile insurance industry," European Journal of Operational Research, Elsevier, vol. 176(1), pages 565-583, January.
    2. Bermúdez, Ll. & Pérez, J.M. & Ayuso, M. & Gómez, E. & Vázquez, F.J., 2008. "A Bayesian dichotomous model with asymmetric link for fraud in insurance," Insurance: Mathematics and Economics, Elsevier, vol. 42(2), pages 779-786, April.
    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. Katja Müller & Hato Schmeiser & Joël Wagner, 2016. "The impact of auditing strategies on insurers’ profitability," Journal of Risk Finance, Emerald Group Publishing, vol. 17(1), pages 46-79, January.
    2. Mercedes Ayuso(universitat de Barcelona) & Miguel Santolino(Universitat de Barcelona), 2009. "Individual prediction of automobile bodily injury claims liabilities," Working Papers in Economics 220, Universitat de Barcelona. Espai de Recerca en Economia.
    3. Benedek Botond & László Ede, 2019. "Identifying Key Fraud Indicators in the Automobile Insurance Industry Using SQL Server Analysis Services," Studia Universitatis Babeș-Bolyai Oeconomica, Sciendo, vol. 64(2), pages 53-71, August.
    4. Botond Benedek & Balint Zsolt Nagy, 2023. "Traditional versus AI-Based Fraud Detection: Cost Efficiency in the Field of Automobile Insurance," Financial and Economic Review, Magyar Nemzeti Bank (Central Bank of Hungary), vol. 22(2), pages 77-98.
    5. Jing Ai & Patrick L. Brockett & Linda L. Golden & Montserrat Guillén, 2013. "A Robust Unsupervised Method for Fraud Rate Estimation," Journal of Risk & Insurance, The American Risk and Insurance Association, vol. 80(1), pages 121-143, March.
    6. Yankol-Schalck, Meryem, 2022. "The value of cross-data set analysis for automobile insurance fraud detection," Research in International Business and Finance, Elsevier, vol. 63(C).
    7. Mercedes Ayuso & Miguel Santolino, 2012. "Forecasting the Maximum Compensation Offer in the Automobile BI Claims Negotiation Process," Group Decision and Negotiation, Springer, vol. 21(5), pages 663-676, September.
    8. Catayoun Azarm & Erman Acar & Mickey van Zeelt, 2024. "On the Potential of Network-Based Features for Fraud Detection," Papers 2402.09495, arXiv.org, revised Feb 2024.
    9. Xia, Changyuan & Yang, Junjie & Yang, Zeng & Chan, Kam C., 2023. "Do directors with foreign experience increase the corporate demand for directors' and officers' liability insurance? Evidence from China," Economic Modelling, Elsevier, vol. 119(C).
    10. Wang, Xiaofang & Zhuang, Jun, 2011. "Balancing congestion and security in the presence of strategic applicants with private information," European Journal of Operational Research, Elsevier, vol. 212(1), pages 100-111, July.
    11. Ming-Jyh Wang & Chieh-Hua Wen & Lawrence W Lan, 2010. "Modelling Different Types of Bundled Automobile Insurance Choice Behaviour: The Case of Taiwan*," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 35(2), pages 290-308, April.
    12. Urbina, Jilber & Guillén, Montserrat, 2013. "An application of capital allocation principles to operational risk," MPRA Paper 75726, University Library of Munich, Germany, revised Dec 2013.
    13. Samuel Antwi & Xicang Zhao, 2012. "National Health Insurance; Claims; Logistic Regression;Odds Ratio; Ghana," International Journal of Business and Social Research, LAR Center Press, vol. 2(7), pages 139-147, December.
    14. Bayerstadler, Andreas & van Dijk, Linda & Winter, Fabian, 2016. "Bayesian multinomial latent variable modeling for fraud and abuse detection in health insurance," Insurance: Mathematics and Economics, Elsevier, vol. 71(C), pages 244-252.
    15. Haupt, Johannes & Bender, Benedict & Fabian, Benjamin & Lessmann, Stefan, 2018. "Robust identification of email tracking: A machine learning approach," European Journal of Operational Research, Elsevier, vol. 271(1), pages 341-356.
    16. Bermúdez, Ll. & Pérez, J.M. & Ayuso, M. & Gómez, E. & Vázquez, F.J., 2008. "A Bayesian dichotomous model with asymmetric link for fraud in insurance," Insurance: Mathematics and Economics, Elsevier, vol. 42(2), pages 779-786, April.
    17. Lessmann, Stefan & Voß, Stefan, 2009. "A reference model for customer-centric data mining with support vector machines," European Journal of Operational Research, Elsevier, vol. 199(2), pages 520-530, December.
    18. Michele Tumminello & Andrea Consiglio & Pietro Vassallo & Riccardo Cesari & Fabio Farabullini, 2023. "Insurance fraud detection: A statistically validated network approach," Journal of Risk & Insurance, The American Risk and Insurance Association, vol. 90(2), pages 381-419, June.
    19. Yiting Xing & Ling Li & Zhuming Bi & Marzena Wilamowska‐Korsak & Li Zhang, 2013. "Operations Research (OR) in Service Industries: A Comprehensive Review," Systems Research and Behavioral Science, Wiley Blackwell, vol. 30(3), pages 300-353, May.
    20. Galeotti, Marcello & Rabitti, Giovanni & Vannucci, Emanuele, 2020. "An evolutionary approach to fraud management," European Journal of Operational Research, Elsevier, vol. 284(3), pages 1167-1177.

    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:2403.06482. 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.