• • 上一篇    下一篇

基于蓄水池抽样的智能医保动态风险决策及应用

龚谊承1,2, 王晓杰1, 邹一鸣1   

  1. 1. 武汉科技大学理学院 武汉 430065;
    2. 冶金工业过程系统科学湖北省重点实验室 武汉科技大学 武汉 430081
  • 收稿日期:2020-12-31 修回日期:2021-08-18 出版日期:2022-04-25 发布日期:2022-06-18
  • 基金资助:
    国家自然科学基金重点项目(72031009)资助课题.

龚谊承, 王晓杰, 邹一鸣. 基于蓄水池抽样的智能医保动态风险决策及应用[J]. 系统科学与数学, 2022, 42(4): 802-817.

GONG Yicheng, WANG Xiaojie, ZOU Yiming. Dynamic Risk Decision of Intelligent Medical Insurance Based on Reservoir Sampling and Its Application[J]. Journal of Systems Science and Mathematical Sciences, 2022, 42(4): 802-817.

Dynamic Risk Decision of Intelligent Medical Insurance Based on Reservoir Sampling and Its Application

GONG Yicheng1,2, WANG Xiaojie1, ZOU Yiming1   

  1. 1. School of Science, Wuhan University of Science and Technology, Wuhan 430065;
    2. Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan University of Science and Technology, Wuhan 430081
  • Received:2020-12-31 Revised:2021-08-18 Online:2022-04-25 Published:2022-06-18
The difficulty of medical insurance risk decision-making in practical applications is that the insured person’s illness is uncertain. For this reason, we try to use machine learning coupled with reservoir sampling to establish a dynamic prediction model to assist medical insurance companies in making intelligent risk decisions. Three aspects were specifically made. First, we build a medical insurance risk decision model, and theoretically we obtain optimal decision rules; then, based on historical data with a fixed sample size, we build a framework for intelligent medical insurance static risk decision-making; finally, to improve static intelligent prediction regarding the lag of risk decision-making guidance, the idea of using machine learning coupled with reservoir algorithm to carry out intelligent dynamic risk decision-making is proposed, dynamic sampling is performed on continuously updated data sets, and a predictive model that is dynamically updated over time is established. Take diabetes as an example of the insured disease, the 2017 Tianchi Precision Medicine Competition-Artificial Intelligence-Assisted Diabetes Risk Prediction Data. In view of the high dimensionality and complex types of data feature variables, the machine learning algorithm selected is random forest. Experiments and comparisons on the training set with the same sample size and the same test set show that the effect of the decision model based on dynamic prediction is better than the static prediction model.

MR(2010)主题分类: 

()
[1] Smith K A, Willis R J, Brooks M. An analysis of customer retention and insurance claim patterns using data mining:A case study. Journal of the Operational Research Society, 2000, 51(5):532-541.
[2] Lowe D J, Parvar J. A logistic regression approach to modelling the contractor's decision to bid. Construction Management&Economics, 2004, 22(6):643-653.
[3] Hua Z, Li S, Tao Z. A rule-based risk decision-making approach and its application in China's customs inspection decision. Journal of the Operational Research Society, 2006, 57(11):1313-1322.
[4] 闫新新,赵珊珊,孙秉赋,等.癌症患者对医疗风险的感知及对临床决策的影响.医学与哲学(B), 2014, 35(6):31-33, 62.(Yan X X, Zhao S S, Sun B F, et al. Cancer patients'perception of medical risks and their influence on clinical decision-making. Medicine&Philosophy (B), 2014, 35(6):31-33, 62.)
[5] 杜梅慧,李莉莉,张璇.基于两步子抽样算法的P2P信用风险预测研究.系统科学与数学, 2021, 41(2):566-576.(Du M H, Li L L, Zhan X. Research on P2P credit risk forecast based on two-step sub-sampling algorithm. Journal of Systems Science and Mathematical Sciences, 2021, 41(2):566-576.)
[6] 陈建中,张辉智.基于Logistic-SVM的文化创意众筹项目违约风险预警研究.系统科学与数学, 2020,40(12):2320-2331.(Chen J Z, Zhang H Z. Research on the early warning of default risk of cultural creative crowdfunding projects based on logistic-SVM. Journal of Systems Science and Mathematical Sciences, 2020, 40(12):2320-2331.)
[7] 佟瑞鹏.基于神经网络的企业安全信用等级评估模式初探.中国科技信息, 2005,(5):107.(Dong R P. A preliminary study on the evaluation model of enterprise security credit rating based on neural network. China Science and Technology Information, 2005,(5):107.)
[8] Lin F, Yeh C C, Lee M Y. The use of hybrid manifold learning and support vector machines in the prediction of business failure. Knowledge-Based Systems, 2011, 24(1):95-101.
[9] Chen M Y. A hybrid model for business failure prediction-Utilization of particle swarm optimization and support vector machines. Neural Network World, 2011, 21(2):129-152.
[10])肖进,刘敦虎,顾新,等.银行客户信用评估动态分类器集成选择模型.管理科学学报, 2015, 18(3):114-126.(Xiao J, Liu D H, Gu X, et al. Integrated selection model of dynamic classifiers for bank customer credit evaluation. Journal of Management Sciences in China, 2015, 18(3):114-126.)
[11] 肖红姗.面向风险决策问题的集成学习模型与算法研究.硕士论文.重庆大学,重庆, 2017.(Xiao H S. Research on integrated learning model and algorithm for risk decision problems. Master's thesis. Chongqing University, Chongqing, 2017.)
[12] 罗森月.用决策树求解风险型决策问题分析.智库时代, 2019,(10):76——77.(Luo S Y. Analysis of solving risky decision problem with decision tree. Think Tank Era, 2019,(10):76-77.)
[13] 李国昌,刘珊珊."互联网金融+PPP"项目风险决策模型分析——基于熵值法与TOPSIS法.铜陵学院学报,2019, 18(3):31-34.(Li G C, Liu S S. "Internet finance+PPP" project risk decision model analysis-Based on entropy method and TOPSIS method. Journal of Tongling University, 2019, 18(3):31-34.)
[14] 黄志刚,刘佳进,林朝颖.基于机器学习的上市公司财报舞弊识别前沿方法比较研究.系统科学与数学, 2020, 40(10):1882-1900.(Huang Z G, Liu J J, Lin C Y. A comparative study of frontier methods of recognizing fraud in financial reports of listed companies based on machine learning. Journal of Systems Science and Mathematical Sciences, 2020, 40(10):1882-1900.)
[15] 琚春华,陈冠宇,鲍福光.基于kNN-Smote-LSTM的消费金融风险检测模型——以信用卡欺诈检测为例.系统科学与数学,2021, 41(2):481-498.(Ju C H, Chen G Y, Bao F G. Consumer finance risk detection model based on kNN-SmoteLSTM-Taking credit card fraud detection as an example. Journal of Systems Science and Mathematical Sciences, 2021, 41(2):481-498.)
[1] 黄爱洁, 陈志翔. 糖尿病血糖调节自抗扰控制器设计[J]. 系统科学与数学, 2021, 41(4): 913-926.
[2] 朱章鹏,陈长波. 基于机器学习的柱形代数分解变元择序[J]. 系统科学与数学, 2020, 40(8): 1492-1506.
[3] 牟唯嫣,王春玲,赵昕. 基于空间填充准则的交叉验证方法及其应用[J]. 系统科学与数学, 2020, 40(2): 382-388.
[4] 黄志刚,刘佳进,林朝颖. 基于机器学习的上市公司财报舞弊识别前沿方法比较研究[J]. 系统科学与数学, 2020, 40(10): 1882-1900.
[5] 刘小弟,朱建军,张世涛,常志朋,王治莹. 犹豫模糊动态灰靶决策方法[J]. 系统科学与数学, 2019, 39(8): 1264-1275.
[6] 蒋敏;孟志青. 多周期多目标条件风险值模型[J]. 系统科学与数学, 2011, 31(4): 414-428.
阅读次数
全文


摘要