arXiv：cs.LG· Bruno Deprez, Wouter Verbeke, Tim Verdonck·· 13 小时前
TabPFN 是车险定价的银弹吗？首个实证评估：索赔频率不敌 GLM，索赔金额可媲美 XGBoost
Is TabPFN the Silver Bullet for Insurance Pricing?
AI 导读
首个针对车险定价的 TabPFN 实证评估显示，这款表格基础模型（TFM）并未稳定超越现有基线：在两个公开的机动车第三者责任险（MTPL）数据集上，其索赔频率表现落后于 GLM，且依赖上下文训练集规模；在数据更稀缺的索赔金额上则与 XGBoost 相当。TabPFN 的推理时间明显更长，尚不足以取代成熟的精算方法。
正文
Abstract:Modelling claim frequency and severity for non-life insurance pricing predominantly relies on generalised linear models (GLMs), with gradient-boosted machines as the leading machine learning alternative. Tabular foundation models (TFMs) present a fundamentally different inference paradigm. By pre-training on large collections of synthetic datasets, TFMs enable inference on new data through in-context learning, without any dataset-specific preprocessing, fitting, or hyperparameter tuning. This paper presents a first empirical evaluation of TabPFN for motor insurance pricing, benchmarking two versions of TabPFN against GLM and XGBoost on two publicly available motor third-party liability (MTPL) datasets. Our results show that TabPFN does not consistently outperform established baselines: it falls behind the GLM on claim frequency, where its performance depends on the size of the in-context training set, but it is competitive on claim severity, where data are scarcer. Its inference times are substantially longer. Although tabular foundation models are promising, particularly in data-scarce settings, TabPFN is not yet ready to replace established actuarial methods for claim frequency.
| Subjects: | Risk Management (q-fin.RM); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.22892 [q-fin.RM] |
| (or arXiv:2605.22892v3 [q-fin.RM] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22892 arXiv-issued DOI via DataCite |
Submission history
From: Bruno Deprez [view email]
[v1]
Thu, 21 May 2026 13:59:06 UTC (51 KB)
[v2]
Mon, 25 May 2026 06:27:59 UTC (51 KB)
[v3]
Fri, 9 Oct 2026 08:53:15 UTC (93 KB)
来源：arXiv：cs.LG · arxiv.org