New approaches in loss reserving with individual models

个别模型损失准备金的新方法

• 批准号: RGPIN-2015-05899
• 负责人: Pigeon, Mathieu
• 金额: $ 0.95万
• 依托单位: Université du Québec à Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=662181
• 关键词: New; approaches; loss; reserving; individual

An insurer is liable for the claims generated by the contracts sold to clients even if payments occur after the end of the contract and all premiums have been received. He must predict the total amount necessary to pay claims that he has legally committed to cover for and to avoid insolvency or a loss of market share. To carry out this task effectively, a model for the development of claims costs is essential. In contrast to traditional approaches, which focus on describing the collective dynamics of the portfolio, individual methods capture the specific dynamics of each claim (or each small group of claims) in order to predict with maximum accuracy, their future development.*** The proposed research program aims at developing and analyzing new insurance models involving individual dynamics and to classify risks from micro- and macro-approaches. The first part is devoted to investigate the "completion risk", i.e., the risk caused by the fact that the insurer must complete the missing part of the development of an open claim on insurer's activities under various individual models, to quantify the impact of various assumptions about individual dynamics on the level of risk and to study the impact of exogenous factors on this risk and how to control it in the portfolio of an insurance company. The second part is dedicated to comparison, classification and integration of risks from both, individual and collective approaches.***From a theoretical perspective, there is only a small set of academic literature on individual models. Solving problems presented in this proposal will yield innovative approaches by developing a new class of models. This will contribute to the advancement of knowledge in loss reserving, ratemaking and reinsurance. I believe that the proposed research program has the potential of shifting the focus in the literature from collective models, which are extensively used in risk models, to individual models and thereby increase the precision of the predictions. From a practical perspective, the results of the proposed research program will enable a more accurate evaluation of the impact of insurers' decisions on the overall risk level and will lead to a greater financial stability for an insurance company.**

保险公司对出售给客户的合同所产生的索赔负有责任，即使付款发生在合同终止后，并且已收到所有保费。他必须预测支付索赔所需的总金额，这些索赔是他在法律上承诺的，以弥补和避免破产或市场份额的损失。为了有效地执行这项任务，开发索赔费用的模式至关重要。与专注于描述投资组合的集体动态的传统方法不同，单独的方法捕捉每个索赔(或每一小组索赔)的特定动态，以便以最大精度预测其未来发展。*拟议的研究计划旨在开发和分析涉及个人动态的新保险模型，并从微观和宏观方法对风险进行分类。第一部分致力于研究“完成风险”，即在不同的个体模型下，保险人必须完成对保险人活动的开放索赔发展的缺失部分所造成的风险，量化关于个体动态的各种假设对风险水平的影响，研究外生因素对这种风险的影响以及如何在保险公司的投资组合中控制这种风险。第二部分致力于从个人和集体的角度对风险进行比较、分类和整合。*从理论的角度来看，关于个体模型的学术文献很少。解决本提案中提出的问题将通过开发一类新的模型来产生创新的方法。这将有助于提高对损失准备金、费率制定和再保险的认识。我相信，拟议的研究计划有可能将国内文献的重点从风险管理模型中广泛使用的集体模型转移到单个模型，从而提高预测的精度。从实践的角度来看，建议的研究计划的结果将使保险公司能够更准确地评估保险公司的决策对整体风险水平的影响，并将导致保险公司更大的财务稳定性。**