用递归推理模型优化保险定价，提升可解释性与效率
Tab-TRM: Tiny Recursive Model for Insurance Pricing on Tabular Data
- 通过可学习的隐状态和答案令牌递归更新特征表示
- 在多个保险数据集上实现比传统模型更高的预测精度
- 适合需要可解释定价模型的保险科技与精算领域
我们提出Tab-TRM（Tabular-Tiny Recursive Model），一种将极小递归模型（TRM）的递归潜在推理范式适配于保险建模的网络架构。受分层推理模型（HRM）及其简化版TRM启发，该模型通过推理输入特征进行预测。它维护两个可学习的隐状态：一个答案令牌和一个推理状态，由紧凑、参数高效的递归网络迭代优化。递归处理层反复根据完整的令牌序列更新推理状态，并据此精炼答案令牌，与迭代保险定价方案高度相似。概念上，Tab-TRM连接了经典精算流程（如迭代广义线性模型拟合与最小偏差校准）与现代机器学习方法（如梯度提升机）。实验表明，其在多个保险数据集上表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。