Medical Insurance Cost Prediction Using Machine Learning

This study explores the application of machine learning (ML) techniques for predicting medical insurance costs, aiming to enhance cost management and improve decision-making for insurers and healthcare providers. Utilizing a dataset comprising demographic, health-related, and historical claims data, we employed various ML algorithms, including linear regression, random forest, XGBoost regression and K- Nearest neighbor methods, to forecast insurance expenditures. The models were evaluated based on accuracy, precision, and recall, with emphasis on feature selection to identify the most influential factors driving costs. Our findings indicate that ML models can effectively predict insurance costs, with ensemble methods yielding the highest accuracy. This research underscores the potential of machine learning in transforming healthcare finance, enabling more accurate pricing strategies, risk assessment, and ultimately leading to improved patient outcomes and operational efficiency. Future work will focus on integrating real-time data and refining predictive models to adapt to changing healthcare trends.