Health Insurance Annual Premium Forecast Analysis

Abstract

This study focuses on predicting an important socioeconomic indicator: health insurance costs and provides an in-depth exploration of the impact of multiple factors on insurance costs. The data used in the study comes from a representative health insurance company, and its data individuals include indicators of multiple dimensions, such as the age, gender, body fat percentage, family size of the insured, as well as whether they have smoking habits and the specific region where they are located. and other information. In order to accurately reveal the impact of these factors on insurance premiums, we adopted a machine learning model, the Lasso regression model, for modeling and prediction, supplemented by the calculation of correlation coefficients to quantify the strength of the relationship between these factors and insurance premiums. After in-depth exploration and analysis, the research results show that among all factors considered, age, body fat percentage and whether you smoke have a significant impact. It is particularly noteworthy that the factor of smoking has the most significant impact on insurance costs. In addition, the study also revealed that women and insured persons living in the southeast region tend to choose higher premiums. These research results not only have a certain enlightenment effect on theoretical research, but also have significant reference value for the practice of the insurance industry. It can help insurance companies more accurately identify and evaluate potential risks, and set more scientific and reasonable insurance rates accordingly.