Prediction of Insurance Cost through ML Structured Algorithm

This study addresses the increased utility of health insurance estimates in the wake of the COVID-19 pandemic We are in a context where many efforts are trying to address this important issue, our study takes a dataset from Kaggle, with 1338 entries that impressively capture the nuances of American medical spending. Our study examines a variety of factors such as age, sex, BMI, smoking and number of children plus to predict health insurance costs. What makes it unique is the use of linear regression to unpack the strong relationship between these factors and insurance costs. We carefully partitioned our data set, with 70% for training, and achieved an impressive 81.3% accuracy. This ethically driven study enhances our understanding of the complexities of post-COVID-19 health insurance spending. The use of linear regression stands out as a powerful rational forecasting tool, and represents a remarkable advancement in healthcare cost forecasting. The importance of the research is to provide insight into the changing landscape of post-pandemic health insurance costs, increase our knowledge, and contribute to decision-making in health care policy.

I. Introduction

The digital health sector has grown tremendously over the years, in terms of infrastructure [1]. At the same time, health insurance in developed countries is facing challenges such as rising health costs and growing unpaid population. This has led governments to allocate resources to support the digital health sector. One area is health insurance, which plays a role in helping individuals manage rare diseases and provides students with affordable medical coverage [2