我院李政宵副教授与大连海事大学航运经济与管理学院余方平教授、张蒙丹硕士、东北财经大学金融学院杨默副教授共同撰写的学术论文“Ship insurance in the era of AI: An intelligent risk profiling system under the POM principles ”于2025年12月被Journal of Risk and Insurance期刊正式接收并在线发表。该期刊创刊于1933年，是保险学界历史悠久、享有盛誉的权威老牌季刊，其年发文量仅30余篇，遴选标准严格。

论文摘要

As the origin of modern commercial insurance, ship insurance underpins global maritime supply chain stability. Yet shipping modernization and AI advances expose three flaws in traditional risk profiling: misalignment with frequency-severity pricing, inadequate for accommodating to complex risk factor system, and lack of data stream adjustment mechanisms. To address these, we propose POM principles (Personalized risk portrait, Omnispective risk factors, and Maneuverable calibration) and an AI framework with three cores: (1) extensible "retrospective + prospective" risk factors; (2) independent AI modules for premium rate/insurance amount prediction; (3) data steam calibration on historical data. Validated via 15,007 records (15 % of China's 2016-2021 registered ships) using random forest regression, it outperforms traditional generalized linear models and mainstream machine learning models in accuracy and risk differentiation. This pioneers intelligent ship insurance profiling, fills gaps in individualized pricing, and offers insights for sectors like aviation insurance, sharing its "premium rate × insurance amount" logic.

作为现代商业保险的起源，船舶保险是全球海运供应链稳定的重要支撑。然而，航运代化与人工智能技术的发展暴露出传统风险画像的三大缺陷：与频率-强度定价体系不匹配、难以适配复杂风险因子系统、缺乏数据流调整机制。为解决上述问题，本文提出POM原则，并构建智能框架，其核心为可扩展的风险因子体系、保费与保额双预测AI模块及数据流校准机制。基于1.5万余条船舶数据的实验表明，该框架预测性能显著优于传统模型。研究开创了智能化船舶保险风险画像的新路径，填补了个性化定价领域的研究空白，其“保费费率×保险金额”双维度定价逻辑可为其他交通运载工具保险等领域提供借鉴。

作者介绍

李政宵，对外经济贸易大学统计与精算学系副教授（链接）