IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2310.12671.html
   My bibliography  Save this paper

Neural networks for insurance pricing with frequency and severity data: a benchmark study from data preprocessing to technical tariff

Author

Listed:
  • Freek Holvoet
  • Katrien Antonio
  • Roel Henckaerts

Abstract

Insurers usually turn to generalized linear models for modelling claim frequency and severity data. Due to their success in other fields, machine learning techniques are gaining popularity within the actuarial toolbox. Our paper contributes to the literature on frequency-severity insurance pricing with machine learning via deep learning structures. We present a benchmark study on four insurance data sets with frequency and severity targets in the presence of multiple types of input features. We compare in detail the performance of: a generalized linear model on binned input data, a gradient-boosted tree model, a feed-forward neural network (FFNN), and the combined actuarial neural network (CANN). Our CANNs combine a baseline prediction established with a GLM and GBM, respectively, with a neural network correction. We explain the data preprocessing steps with specific focus on the multiple types of input features typically present in tabular insurance data sets, such as postal codes, numeric and categorical covariates. Autoencoders are used to embed the categorical variables into the neural network and we explore their potential advantages in a frequency-severity setting. Finally, we construct global surrogate models for the neural nets' frequency and severity models. These surrogates enable the translation of the essential insights captured by the FFNNs or CANNs to GLMs. As such, a technical tariff table results that can easily be deployed in practice.

Suggested Citation

  • Freek Holvoet & Katrien Antonio & Roel Henckaerts, 2023. "Neural networks for insurance pricing with frequency and severity data: a benchmark study from data preprocessing to technical tariff," Papers 2310.12671, arXiv.org, revised Oct 2023.
  • Handle: RePEc:arx:papers:2310.12671
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2310.12671
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yue Liu & Bing-Jie Wang & Shao-Gao Lv, 2014. "Using Multi-class AdaBoost Tree for Prediction Frequency of Auto Insurance," Journal of Applied Finance & Banking, SCIENPRESS Ltd, vol. 4(5), pages 1-4.
    2. Denuit, Michel & Hainaut, Donatien & Trufin, Julien, 2020. "Effective Statistical Learning Methods for Actuaries II : Tree-Based Methods and Extensions," LIDAM Reprints ISBA 2020035, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    3. Donatien Hainaut & Julien Trufin & Michel Denuit, 2022. "Response versus gradient boosting trees, GLMs and neural networks under Tweedie loss and log-link," Scandinavian Actuarial Journal, Taylor & Francis Journals, vol. 2022(10), pages 841-866, November.
    4. de Jong,Piet & Heller,Gillian Z., 2008. "Generalized Linear Models for Insurance Data," Cambridge Books, Cambridge University Press, number 9780521879149.
    5. Meng, Shengwang & Wang, He & Shi, Yanlin & Gao, Guangyuan, 2022. "Improving Automobile Insurance Claims Frequency Prediction With Telematics Car Driving Data," ASTIN Bulletin, Cambridge University Press, vol. 52(2), pages 363-391, May.
    6. Yi Yang & Wei Qian & Hui Zou, 2018. "Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Models," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 36(3), pages 456-470, July.
    7. Roel Henckaerts & Katrien Antonio & Maxime Clijsters & Roel Verbelen, 2018. "A data driven binning strategy for the construction of insurance tariff classes," Scandinavian Actuarial Journal, Taylor & Francis Journals, vol. 2018(8), pages 681-705, September.
    8. Roel Henckaerts & Marie-Pier Côté & Katrien Antonio & Roel Verbelen, 2021. "Boosting Insights in Insurance Tariff Plans with Tree-Based Machine Learning Methods," North American Actuarial Journal, Taylor & Francis Journals, vol. 25(2), pages 255-285, April.
    9. Gao, Guangyuan & Meng, Shengwang & Wüthrich, Mario V., 2022. "What can we learn from telematics car driving data: A survey," Insurance: Mathematics and Economics, Elsevier, vol. 104(C), pages 185-199.
    10. Delong, Łukasz & Kozak, Anna, 2023. "The use of autoencoders for training neural networks with mixed categorical and numerical features," ASTIN Bulletin, Cambridge University Press, vol. 53(2), pages 213-232, May.
    11. Kevin Kuo & Ronald Richman, 2021. "Embeddings and Attention in Predictive Modeling," Papers 2104.03545, arXiv.org.
    12. Hainaut, Donatien & Trufin, Julien & Denuit, Michel, 2022. "Response versus gradient boosting trees, GLMs and neural networks under Tweedie loss and log-link," LIDAM Reprints ISBA 2022037, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    13. Antonio, Katrien & Frees, Edward W. & Valdez, Emiliano A., 2010. "A Multilevel Analysis of Intercompany Claim Counts," ASTIN Bulletin, Cambridge University Press, vol. 40(1), pages 151-177, May.
    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. Hainaut, Donatien & Trufin, Julien & Denuit, Michel, 2021. "Response versus gradient boosting trees, GLMs and neural networks under Tweedie loss and log-link," LIDAM Discussion Papers ISBA 2021012, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    2. Zuleyka Díaz Martínez & José Fernández Menéndez & Luis Javier García Villalba, 2023. "Tariff Analysis in Automobile Insurance: Is It Time to Switch from Generalized Linear Models to Generalized Additive Models?," Mathematics, MDPI, vol. 11(18), pages 1-16, September.
    3. Zhiyu Quan & Changyue Hu & Panyi Dong & Emiliano A. Valdez, 2024. "Improving Business Insurance Loss Models by Leveraging InsurTech Innovation," Papers 2401.16723, arXiv.org.
    4. Willame, Gireg & Trufin, Julien & Denuit, Michel, 2023. "Boosted Poisson regression trees: A guide to the BT package in R," LIDAM Discussion Papers ISBA 2023008, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    5. Christopher Blier-Wong & Hélène Cossette & Luc Lamontagne & Etienne Marceau, 2020. "Machine Learning in P&C Insurance: A Review for Pricing and Reserving," Risks, MDPI, vol. 9(1), pages 1-26, December.
    6. Marian Reiff & Erik Šoltés & Silvia Komara & Tatiana Šoltésová & Silvia Zelinová, 2022. "Segmentation and estimation of claim severity in motor third-party liability insurance through contrast analysis," Equilibrium. Quarterly Journal of Economics and Economic Policy, Institute of Economic Research, vol. 17(3), pages 803-842, September.
    7. Trufin, Julien & Denuit, Michel, 2021. "Boosting cost-complexity pruned trees On Tweedie responses: the ABT machine," LIDAM Discussion Papers ISBA 2021015, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    8. Katrien Antonio & Emiliano Valdez, 2012. "Statistical concepts of a priori and a posteriori risk classification in insurance," AStA Advances in Statistical Analysis, Springer;German Statistical Society, vol. 96(2), pages 187-224, June.
    9. Hu, Changyue & Quan, Zhiyu & Chong, Wing Fung, 2022. "Imbalanced learning for insurance using modified loss functions in tree-based models," Insurance: Mathematics and Economics, Elsevier, vol. 106(C), pages 13-32.
    10. Tingting Chen & Anthony Francis Desmond & Peter Adamic, 2023. "Generalized Additive Modelling of Dependent Frequency and Severity Distributions for Aggregate Claims," Journal of Statistical and Econometric Methods, SCIENPRESS Ltd, vol. 12(4), pages 1-1.
    11. Simon CK Lee, 2020. "Delta Boosting Implementation of Negative Binomial Regression in Actuarial Pricing," Risks, MDPI, vol. 8(1), pages 1-21, February.
    12. Denuit, Michel & Trufin, Julien & Verdebout, Thomas, 2022. "Boosting on the responses with Tweedie loss functions," LIDAM Discussion Papers ISBA 2022039, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    13. Benjamin Avanzi & Greg Taylor & Melantha Wang & Bernard Wong, 2023. "Machine Learning with High-Cardinality Categorical Features in Actuarial Applications," Papers 2301.12710, arXiv.org.
    14. Yang Lu, 2019. "Flexible (panel) regression models for bivariate count–continuous data with an insurance application," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 182(4), pages 1503-1521, October.
    15. Avanzi, Benjamin & Taylor, Greg & Wong, Bernard & Yang, Xinda, 2021. "On the modelling of multivariate counts with Cox processes and dependent shot noise intensities," Insurance: Mathematics and Economics, Elsevier, vol. 99(C), pages 9-24.
    16. Chenglong Ye & Lin Zhang & Mingxuan Han & Yanjia Yu & Bingxin Zhao & Yuhong Yang, 2022. "Combining Predictions of Auto Insurance Claims," Econometrics, MDPI, vol. 10(2), pages 1-15, April.
    17. Aivars Spilbergs & Andris Fomins & Māris Krastiņš, 2022. "Multivariate Modelling of Motor Third Party Liability Insurance Claims," European Journal of Business Science and Technology, Mendel University in Brno, Faculty of Business and Economics, vol. 8(1), pages 5-18.
    18. Deprez, Laurens & Antonio, Katrien & Boute, Robert, 2021. "Pricing service maintenance contracts using predictive analytics," European Journal of Operational Research, Elsevier, vol. 290(2), pages 530-545.
    19. Martin Branda, 2014. "Optimization Approaches to Multiplicative Tariff of Rates Estimation in Non-Life Insurance," Asia-Pacific Journal of Operational Research (APJOR), World Scientific Publishing Co. Pte. Ltd., vol. 31(05), pages 1-17.
    20. Jeonghwan Kim & Woojoo Lee, 2019. "On testing the hidden heterogeneity in negative binomial regression models," Metrika: International Journal for Theoretical and Applied Statistics, Springer, vol. 82(4), pages 457-470, 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:2310.12671. 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.