IDEAS home Printed from https://ideas.repec.org/a/gam/jrisks/v12y2023i1p4-d1307953.html
   My bibliography  Save this article

Advancing the Use of Deep Learning in Loss Reserving: A Generalized DeepTriangle Approach

Author

Listed:
  • Yining Feng

    (AXA, 20 Gracechurch Street, London EC3V 0BG, UK)

  • Shuanming Li

    (Centre for Actuarial Studies, Department of Economics, The University of Melbourne, Melbourne, VIC 3010, Australia)

Abstract

This paper proposes a generalized deep learning approach for predicting claims developments for non-life insurance reserving. The generalized approach offers more flexibility and accuracy in solving actuarial reserving problems. It predicts claims outstanding weighted by exposure instead of loss ratio to remove subjectivity associated with premium weighting. Chain-ladder predicted outstanding claims are used as part of the multi-task learning to remove the dependence on case estimates. Grid-search is introduced for hyperparameter tuning to improve model performance. Performance-wise, the Generalized DeepTriangle outperforms both traditional chain-ladder methodology, the automated machine learning approaches (AutoML), and the original DeepTriangle model.

Suggested Citation

  • Yining Feng & Shuanming Li, 2023. "Advancing the Use of Deep Learning in Loss Reserving: A Generalized DeepTriangle Approach," Risks, MDPI, vol. 12(1), pages 1-14, December.
    • Handle: RePEc:gam:jrisks:v:12:y:2023:i:1:p:4-:d:1307953
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-9091/12/1/4/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-9091/12/1/4/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. England, Peter & Verrall, Richard, 1999. "Analytic and bootstrap estimates of prediction errors in claims reserving," Insurance: Mathematics and Economics, Elsevier, vol. 25(3), pages 281-293, December.
    2. Mack, Thomas, 1993. "Distribution-free Calculation of the Standard Error of Chain Ladder Reserve Estimates," ASTIN Bulletin, Cambridge University Press, vol. 23(2), pages 213-225, November.
    3. Hesselager, Ole, 1994. "A Markov Model for Loss Reserving," ASTIN Bulletin, Cambridge University Press, vol. 24(2), pages 183-193, November.
    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. Emmanuel Jordy Menvouta & Jolien Ponnet & Robin Van Oirbeek & Tim Verdonck, 2022. "mCube: Multinomial Micro-level reserving Model," Papers 2212.00101, arXiv.org.
    2. Gian Paolo Clemente & Nino Savelli & Diego Zappa, 2019. "Modelling Outstanding Claims with Mixed Compound Processes in Insurance," International Business Research, Canadian Center of Science and Education, vol. 12(3), pages 123-138, March.
    3. Francis Duval & Mathieu Pigeon, 2019. "Individual Loss Reserving Using a Gradient Boosting-Based Approach," Risks, MDPI, vol. 7(3), pages 1-18, July.
    4. Pitselis, Georgios & Grigoriadou, Vasiliki & Badounas, Ioannis, 2015. "Robust loss reserving in a log-linear model," Insurance: Mathematics and Economics, Elsevier, vol. 64(C), pages 14-27.
    5. Carnevale Giulio Ercole & Clemente Gian Paolo, 2020. "A Bayesian Internal Model for Reserve Risk: An Extension of the Correlated Chain Ladder," Risks, MDPI, vol. 8(4), pages 1-20, November.
    6. Eduardo Ramos-P'erez & Pablo J. Alonso-Gonz'alez & Jos'e Javier N'u~nez-Vel'azquez, 2020. "Stochastic reserving with a stacked model based on a hybridized Artificial Neural Network," Papers 2008.07564, arXiv.org.
    7. Liivika Tee & Meelis Käärik & Rauno Viin, 2017. "On Comparison of Stochastic Reserving Methods with Bootstrapping," Risks, MDPI, vol. 5(1), pages 1-21, January.
    8. Bohnert, Alexander & Gatzert, Nadine & Kolb, Andreas, 2016. "Assessing inflation risk in non-life insurance," Insurance: Mathematics and Economics, Elsevier, vol. 66(C), pages 86-96.
    9. Mat'uv{s} Maciak & Ostap Okhrin & Michal Pev{s}ta, 2019. "Infinitely Stochastic Micro Forecasting," Papers 1908.10636, arXiv.org, revised Sep 2019.
    10. Gareth W. Peters & Mario V. Wuthrich & Pavel V. Shevchenko, 2010. "Chain ladder method: Bayesian bootstrap versus classical bootstrap," Papers 1004.2548, arXiv.org.
    11. Klaus Schmidt, 2012. "Loss prediction based on run-off triangles," AStA Advances in Statistical Analysis, Springer;German Statistical Society, vol. 96(2), pages 265-310, June.
    12. Verrall, R.J. & England, P.D., 2005. "Incorporating expert opinion into a stochastic model for the chain-ladder technique," Insurance: Mathematics and Economics, Elsevier, vol. 37(2), pages 355-370, October.
    13. Verrall, R. J., 2000. "An investigation into stochastic claims reserving models and the chain-ladder technique," Insurance: Mathematics and Economics, Elsevier, vol. 26(1), pages 91-99, February.
    14. Arthur Charpentier & Mathieu Pigeon, 2016. "Macro vs. Micro Methods in Non-Life Claims Reserving (an Econometric Perspective)," Risks, MDPI, vol. 4(2), pages 1-18, May.
    15. Wahl, Felix & Lindholm, Mathias & Verrall, Richard, 2019. "The collective reserving model," Insurance: Mathematics and Economics, Elsevier, vol. 87(C), pages 34-50.
    16. Alexandre Boumezoued & Yoboua Angoua & Laurent Devineau & Jean-Philippe Boisseau, 2011. "One-year reserve risk including a tail factor: closed formula and bootstrap approaches," Working Papers hal-00605329, HAL.
    17. László Martinek, 2019. "Analysis of Stochastic Reserving Models By Means of NAIC Claims Data," Risks, MDPI, vol. 7(2), pages 1-27, June.
    18. Taylor, Greg, 2021. "A special Tweedie sub-family with application to loss reserving prediction error," Insurance: Mathematics and Economics, Elsevier, vol. 101(PB), pages 262-288.
    19. Jorge De Andrés-Sánchez, 2024. "Calculating Insurance Claim Reserves with an Intuitionistic Fuzzy Chain-Ladder Method," Mathematics, MDPI, vol. 12(6), pages 1-24, March.
    20. Peters, Gareth W. & Wüthrich, Mario V. & Shevchenko, Pavel V., 2010. "Chain ladder method: Bayesian bootstrap versus classical bootstrap," Insurance: Mathematics and Economics, Elsevier, vol. 47(1), pages 36-51, August.

    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:12:y:2023:i:1:p:4-:d:1307953. 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.