当前位置: X-MOL 学术North American Actuarial Journal › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Boosting Insights in Insurance Tariff Plans with Tree-Based Machine Learning Methods
North American Actuarial Journal Pub Date : 2020-07-13 , DOI: 10.1080/10920277.2020.1745656
Roel Henckaerts 1, 2 , Marie-Pier Côté 3 , Katrien Antonio 1, 2, 4 , Roel Verbelen 1, 2
Affiliation  

Pricing actuaries typically operate within the framework of generalized linear models (GLMs). With the upswing of data analytics, our study puts focus on machine learning methods to develop full tariff plans built from both the frequency and severity of claims. We adapt the loss functions used in the algorithms such that the specific characteristics of insurance data are carefully incorporated: highly unbalanced count data with excess zeros and varying exposure on the frequency side combined with scarce but potentially long-tailed data on the severity side. A key requirement is the need for transparent and interpretable pricing models that are easily explainable to all stakeholders. We therefore focus on machine learning with decision trees: Starting from simple regression trees, we work toward more advanced ensembles such as random forests and boosted trees. We show how to choose the optimal tuning parameters for these models in an elaborate cross-validation scheme. In addition, we present visualization tools to obtain insights from the resulting models, and the economic value of these new modeling approaches is evaluated. Boosted trees outperform the classical GLMs, allowing the insurer to form profitable portfolios and to guard against potential adverse risk selection.



中文翻译:

使用基于树的机器学习方法提高对保险关税计划的洞察力

定价精算师通常在广义线性模型 (GLM) 的框架内运作。随着数据分析的兴起,我们的研究将重点放在机器学习方法上,以根据索赔的频率和严重程度制定完整的关税计划。我们调整算法中使用的损失函数,以便仔细整合保险数据的特定特征:高度不平衡的计数数据,具有过多的零和频率侧的不同暴露,以及严重性侧的稀缺但可能长尾的数据。一个关键要求是需要透明且可解释的定价模型,这些模型易于向所有利益相关者解释。因此,我们专注于使用决策树进行机器学习:从简单的回归树开始,我们致力于更高级的集成,例如随机森林和增强树。我们展示了如何在精心设计的交叉验证方案中为这些模型选择最佳调整参数。此外,我们提供了可视化工具以从结果模型中获取洞察力,并评估这些新建模方法的经济价值。提升树的表现优于经典的 GLM,允许保险公司形成有利可图的投资组合并防范潜在的不利风险选择。

更新日期:2020-07-13
down
wechat
bug