<![CDATA[Technological developments such as telemedicine and big data analysis have had a significant impact on the health insurance industry. It is very difficult to make wise decisions if customers do not understand the cost of insurance. Age, gender, medical history, region, smoking, and body mass index (BMI) are a number of variables used to determine the variables that contribute to health insurance costs. Multiple linear regression was used to identify variables that contribute to predicting relative health insurance costs. Multiple linear regression analysis, also known as multiple regression analysis, is a regression model that involves more than one independent variable. This is determined by using statistical software to determine which independent variables have a significant influence on the dependent variable. The value of using multiple linear regression is primarily related to the need for prediction of insurance costs. In the RapidMiner tool, the linear regression operator is used to perform linear regression calculations. From a total of 1338 datasets, the data is divided into two parts. 90% is used as training data (with a total of 1204 data) and 10% is used as test data (with a total of 134 data). The results of the analysis show that independent factors such as smoking status, age, and body mass index have a significant correlation with insurance premium costs. The value 5891.019 was generated from model evaluation using Root Mean Squared Error (RMSE). The strong correlation between smoking status and premium costs, along with positive correlations with age and body mass index (BMI), suggests that premium costs increase with increasing age and weight category.]]>
Copyrights © 2024
