大数据背景下健康保险动态定价机制研究——基于变换的隐马尔可夫模型

A Research on Dynamic Pricing Mechanism of Health Insurance amid the Big Data Background——Based on Converted Hidden Markov Model

健康保险作为有效的市场化健康风险管理工具逐渐受到青睐。同时,物联网和大数据等创新科技的应用使得医疗健康相关的数据大幅增加且以极快的速度更新,给传统健康保险定价带来巨大挑战。在此背景下,基于大数据背景展开健康保险动态定价研究具有重要意义。本文基于大数据技术构建变换的隐马尔可夫模型,将被保险人多维度健康管理数据合理引入,进行更精准的健康风险预测,并基于奖惩机制实时对健康保险费率进行动态调整。研究发现,相对于传统定价模型,本文所搭建的健康保险费率动态调整机制不但能够防范逆选择风险,还能在很大程度上缓解道德风险,并基于健康管理理念有效激励被保险人主动进行风险控制,对健康保险动态定价的理论探索和实践检验具有一定启发。

As an effective market-oriented health risk management tool, health insurance has been widely accepted.At the same time, the application of innovative technologies such as the Internet of Things and big data has led to a huge increase in the amount of medical and health-related data, which is updated at a fast speed, posing a huge challenge to the pricing of traditional health insurance.In this context, it is of great significance to develop dynamic pricing of health insurance based on big data.In this paper, based on big data technology, the converted hidden Markov model was constructed, and the multi-dimensional health management data of the insured were reasonably introduced to predict health risks more accurately, and the health insurance premium rate was dynamically adjusted in real time based on the reward and punishment mechanism.The study finds that compared with the traditional pricing model, the premium rate dynamic adjustment mechanism proposed by this paper can not only prevent adverse selection risk but also largely alleviate the risk of moral hazard.Moreover, based on the concept of health management, the insured is effectively encouraged to take the initiative to control risks.This brings certain inspiration to the theoretical exploration and practical test of health insurance dynamic pricing.