Hybrid Regression Model for Medical Insurance Cost Prediction and Recommendation
N. Venkata Sailaja, Mounika Karakavalasa, Meera Katkam, M. Devipriya, M. U. Sreeja, D. N. Vasundhara
Abstract
As the global value of gross insurance premiums continues to rise beyond $5 trillion, we know that the majority of these costs are avoidable. The cost prediction of people's medical insurance is a useful method for improving the transparency of health care. We use different regression models to analyze personal health data in order to predict insurance amounts for individuals in this study. The cost of insurance premiums is influenced by a number of factors. Health insurers would benefit from using a Stacking Regression model to predict insurance costs for individuals. According to this perception using recommendation graphs, a person can lower his insurance costs by lowering his BMI, moving to a different area, or switching to a non-smoker.