An Ensemble Methods for Medical Insurance Costs Prediction Task

作     者：Nataliya Shakhovska Nataliia Melnykova Valentyna Chopiyak Michal Gregus ml 

作者机构：Department of Artificial IntelligenceLviv Polytechnic National UniversityLviv79013Ukraine Department of Clinical Immunology and AllergologyDanylo Halytsky Lviv National Medical UniversityLviv79010Ukraine Faculty of ManagementComenius UniversityBratislava81499Slovakia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第2期

页      面：3969-3984页

核心收录：

学科分类：0711[理学-系统科学] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

基　　金：National Research Foundation of Ukraine 

主　　题：Healthcare medical insurance prediction task machine learning ensemble data analysis 

摘      要：The paper reports three new ensembles of supervised learning predictors for managing medical insurance *** open dataset is used for data analysis methods *** usage of artificial intelligence in the management of financial risks will facilitate economic wear time and money and protect patients’*** learning is associated withmany expectations,but its quality is determined by choosing a good algorithm and the proper steps to plan,develop,and implement the *** paper aims to develop three new ensembles for individual insurance costs prediction to provide high prediction *** coefficient and Boruta algorithm are used for feature *** boosting,stacking,and bagging ensembles are built.A comparison with existing machine learning algorithms is *** modes based on regression tree and stochastic gradient descent is *** CART and Random Forest algorithms are *** boosting and stacking ensembles shown better accuracy than *** tuning parameters for boosting do not allow to decrease the RMSE ***,bagging shows its weakness in generalizing the *** stacking is developed using K Nearest Neighbors(KNN),Support Vector Machine(SVM),Regression Tree,Linear Regression,Stochastic Gradient *** random forest(RF)algorithm is used to combine the *** hundred trees are built *** Square Error(RMSE)has lifted the to 3173.213 in comparison with other *** quality of the developed ensemble for RootMean Squared Error metric is 1.47 better than for the best weak predictor(SVR).