IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2601.07675.html

Tab-TRM: Tiny Recursive Model for Insurance Pricing on Tabular Data

Author

Listed:
  • Kishan Padayachy
  • Ronald Richman
  • Mario V. Wuthrich

Abstract

We introduce Tab-TRM (Tabular-Tiny Recursive Model), a network architecture that adapts the recursive latent reasoning paradigm of Tiny Recursive Models (TRMs) to insurance modeling. Drawing inspiration from both the Hierarchical Reasoning Model (HRM) and its simplified successor TRM, the Tab-TRM model makes predictions by reasoning over the input features. It maintains two learnable latent tokens - an answer token and a reasoning state - that are iteratively refined by a compact, parameter-efficient recursive network. The recursive processing layer repeatedly updates the reasoning state given the full token sequence and then refines the answer token, in close analogy with iterative insurance pricing schemes. Conceptually, Tab-TRM bridges classical actuarial workflows - iterative generalized linear model fitting and minimum-bias calibration - on the one hand, and modern machine learning, in terms of Gradient Boosting Machines, on the other.

Suggested Citation

  • Kishan Padayachy & Ronald Richman & Mario V. Wuthrich, 2026. "Tab-TRM: Tiny Recursive Model for Insurance Pricing on Tabular Data," Papers 2601.07675, arXiv.org.
    • Handle: RePEc:arx:papers:2601.07675
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2601.07675
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Richman, Ronald, 2021. "AI in actuarial science – a review of recent advances – part 2," Annals of Actuarial Science, Cambridge University Press, vol. 15(2), pages 230-258, July.
    2. 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.
    3. Alexej Brauer, 2023. "Enhancing Actuarial Non-Life Pricing Models via Transformers," Papers 2311.07597, arXiv.org, revised Jun 2024.
    4. Richman, Ronald, 2021. "AI in actuarial science – a review of recent advances – part 1," Annals of Actuarial Science, Cambridge University Press, vol. 15(2), pages 207-229, July.
    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. Li, Li & Li, Han & Panagiotelis, Anastasios, 2025. "Boosting domain-specific models with shrinkage: An application in mortality forecasting," International Journal of Forecasting, Elsevier, vol. 41(1), pages 191-207.
    2. Giorgio Alfredo Spedicato & Christophe Dutang & Quentin Guibert, 2025. "Adjusting Manual Rates to Own Experience: Comparing the Credibility Approach to Machine Learning," Post-Print hal-04821310, HAL.
    3. Freek Holvoet & Christopher Blier-Wong & Katrien Antonio, 2025. "A multi-view contrastive learning framework for spatial embeddings in risk modelling," Papers 2511.17954, arXiv.org.
    4. Aleksandar Arandjelovi'c & Julia Eisenberg, 2024. "Optimal risk mitigation by deep reinsurance," Papers 2408.06168, arXiv.org, revised Nov 2025.
    5. Jamotton, Charlotte & Hainaut, Donatien, 2024. "Latent Dirichlet Allocation for structured insurance data," LIDAM Discussion Papers ISBA 2024008, Université catholique de Louvain, Institute of Statistics, Biostatistics and Actuarial Sciences (ISBA).
    6. Diego Zappa & Gian Paolo Clemente & Francesco Della Corte & Nino Savelli, 2023. "Editorial on the Special Issue on Insurance: complexity, risks and its connection with social sciences," Quality & Quantity: International Journal of Methodology, Springer, vol. 57(2), pages 125-130, December.
    7. Zhu, Felix & Dong, Yumo & Huang, Fei, 2025. "Data-rich economic forecasting for actuarial applications," Insurance: Mathematics and Economics, Elsevier, vol. 124(C).
    8. Katrien Antonio & Christophe Dutang & Andreas Tsanakas, 2021. "Editorial," Post-Print hal-04748464, HAL.
    9. Wang, Zhihao & Shi, Yanlin & Gao, Guangyuan, 2025. "Additive tree latent variable models with applications to insurance loss prediction," Insurance: Mathematics and Economics, Elsevier, vol. 125(C).
    10. Jaiswal, Rachana & Gupta, Shashank & Tiwari, Aviral Kumar, 2024. "Big data and machine learning-based decision support system to reshape the vaticination of insurance claims," Technological Forecasting and Social Change, Elsevier, vol. 209(C).
    11. Francesca Perla & Salvatore Scognamiglio, 2023. "Locally-coherent multi-population mortality modelling via neural networks," Decisions in Economics and Finance, Springer;Associazione per la Matematica, vol. 46(1), pages 157-176, June.
    12. Simon Hatzesberger & Iris Nonneman, 2025. "Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT," Papers 2506.18942, arXiv.org.
    13. Hung-Tsung Hsiao & Chou-Wen Wang & I.-Chien Liu & Ko-Lun Kung, 2024. "Mortality improvement neural-network models with autoregressive effects," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 49(2), pages 363-383, April.
    14. Corsaro, Stefania & Marino, Zelda & Scognamiglio, Salvatore, 2024. "Quantile mortality modelling of multiple populations via neural networks," Insurance: Mathematics and Economics, Elsevier, vol. 116(C), pages 114-133.
    15. Yang Qiao & Chou-Wen Wang & Wenjun Zhu, 2024. "Machine learning in long-term mortality forecasting," The Geneva Papers on Risk and Insurance - Issues and Practice, Palgrave Macmillan;The Geneva Association, vol. 49(2), pages 340-362, April.
    16. Benjamin Avanzi & Greg Taylor & Melantha Wang & Bernard Wong, 2023. "Machine Learning with High-Cardinality Categorical Features in Actuarial Applications," Papers 2301.12710, arXiv.org.
    17. Yu Wang, Muhammad Asraf bin Abdullah, 2024. "Time Series Analysis and Optimization of the Prediction Model of Agricultural Insurance Loss Ratio," Research on World Agricultural Economy, Nan Yang Academy of Sciences Pte Ltd (NASS), vol. 5(4), November.
    18. Henning Zakrisson & Mathias Lindholm, 2025. "A tree-based varying coefficient model," Computational Statistics, Springer, vol. 40(9), pages 5105-5134, December.
    19. Ronald Richman & Salvatore Scognamiglio & Mario V. Wuthrich, 2024. "The Credibility Transformer," Papers 2409.16653, arXiv.org.
    20. Yue Zhang & Yuantao Xie, 2025. "Risk Measurement of TAVR Surgical Complications Based on Unbalanced Multilabel Classification Approaches," Mathematics, MDPI, vol. 13(13), pages 1-18, June.

    More about this item

    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:2601.07675. 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.