Medical Insurance Cost Analysis and Prediction using Machine Learning

Health insurance is a type of insurance which covers the entire or a portion of the risk that a person might require medical care. Humans have encountered several new viral infectious diseases in the span of the last 20 years as a result of developing and re-emerging infectious illnesses. As a result, the price and necessity of insurances are likewise steadily rising. Nowadays, it is a legal need in many nations to have health insurance, and hospitals may refuse to treat you if you don't have it. Since almost everything in the world become digital, including health insurance, people are becoming more aware of insurance, which will be a tremendous advantage in the future. Therefore, this research intends to raise public awareness about insurances so that they may obtain them at a fair and precise price. It is crucial to take into account several variables to promote the adoption of health insurance, including people's attitudes toward purchasing insurance, their decision-making processes, and factors affecting their demand- and supply-side perceptions of insurance. Moreover, awareness levels may have a significant impact on new and renewed participation in health insurance programs. The effectiveness of these algorithms has been compared using three regression models: Linear Regression, Support Vector, and Random Forest Regressors. The models were trained on a dataset, and this training helped with the predictions. The quantity predicted and the actual data were then compared to test and validate the model. The accuracy levels of these models were contrasted. When compared to other algorithms that have been tried, since it needs considerably less computation time to achieve the performance metric with the maximum percentage of accuracy rate of 87%, approach is best suited in Random Forest Regressor