International Research Journal of Education and Technology

This initiative entails the development of a health insurance prediction system utilizing machine learning. Given the heightened significance of health insurance post the Covid-19 pandemic, numerous endeavors have been made to address this issue. Analyzing the factors influencing health insurance costs poses a considerable challenge, and employing a regression model proves effective in comprehending intricate patterns for predicting medical insurance expenses. The dataset utilized for this study was sourced from Kaggle.

This project employs machine learning algorithms to establish a connection between medical costs. The objective is to devise a methodology for predicting healthcare expenses, leveraging machine learning algorithms to guide individuals toward more affordable options. Furthermore, this technology can assist policymakers in identifying providers with higher costs, enabling potential corrective measures. The Random Forest algorithm is employed to forecast insurance costs in this study. Various machine learning models, such as KNN and Linear Regression, will be

experimented with on the same dataset to compare results. Early estimation of health insurance expenses is beneficial, preventing individuals from potentially investing in unnecessary and costly coverage. While our research does not provide specific amounts tailored to individual insurance providers, it does offer a general understanding of the potential costs individuals may encounter in securing their health insurance.