1 research outputs found
Predictive Model for Computing Health Insurance Premium Rates Using Machine Learning Algorithms
No full textThe health care systems depend heavily on out-of-pocket payments, the mechanism that is a barrier to universal health coverage, as it contributes to inefficiency, inequity and cost. To solve this challenge, people are encouraged to enrol on health insurance schemes to reduce the burden of out-of-pocket payments. There is a strong need for insurance companies to develop models that accurately predict medical expenses for the insured population. The variables; Age, sex, body mass index, number of children and region attributes were used to formulate a predictive model to determine health insurance charges using different Machine learning algorithms techniques. The findings showed that the following variables were significant; age (p = 0.000), BMI (p = 0.001), smoking (p = 0.000) and region (0.046). Therefore, these attributes can be said to be the determinants of health insurance charges. Five (5) models that were used in predictive analysis were evaluated. These models were Multiple Linear Regression (MLR), K-nearest Neighbors (KNN), Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (Xgboosting) and Random Forest Regression (RFR) The models’ performance evaluation findings indicated Gradient Boosting and RFR were the best models in prediction with the following values R2 = 85.5%, MAE = 2688.2, RMSE = 4748.7 and R2 = 85.3%, MAE = 2726.4, RMSE = 4783.8 respectively. The insurance companies that seek to develop a model for prediction premiums are recommended to use Extreme Gradient Boosting and RFR for a more accurate mode
