Data-Based Health Insurance Premium Modeling at KUD Tirta Kencana Using a Machine Learning Approach

Abstract

The Village Unit Cooperative (KUD) plays a strategic role in improving the economic welfare of rural communities. However, attention to the health aspects of members is often not a priority. This study aims to analyze the health insurance costs required by members of the Tirta Kencana KUD in Kuantan Singingi District using a data-based approach and predictive modeling. The methods used include collecting membership and health claim data, processing the data using Principal Component Analysis (PCA), and applying predictive algorithms to estimate ideal and sustainable insurance costs. The analysis results indicate a significant correlation between age, membership status, and health history with the amount of premiums that should be covered. The predictive model successfully identified the optimal premium scheme with a predictive accuracy of 92%. These findings are expected to serve as a basis for policy-making in planning more efficient and equitable cooperative-based insurance. This research also opens opportunities for the application of data science in optimizing community-based microhealth systems.