Medical Insurance Price Prediction Using Xai

Abstract

The need for clear and precise medical insurance pricing has increased, which has prompted research into sophisticated predictive modelling methods. This paper focuses on Medical Insurance Price Prediction using Explainable Artificial Intelligence (XAI) methods, aiming to provide interpretable insights into premium pricing. A dataset comprising ten critical factors, including age, medical history, chronic diseases, surgeries, and family cancer history,serves as the foundation for the model’s training and evaluation. By utilising machine learning models such as Support Vector Machines (SVM), Random Forest, and Extreme Gradient Boosting (XGB), we hope to accurately and interpretable forecast premium prices. The implementation of XAI techniques is central to this study. The main factors influencing premium pricing are identified by SHapley Additive exPlanations (SHAP), which quantifies the contribution of each feature to the model’s predictions.Partial Dependency Plots (PDP) and Individual Conditional Expectations (ICE) are also used to visualise feature interactions and offer detailed, instance-specific interpretations. Our findings show how well the suggested models predict insurance premiums and provide useful information about the factors that influence premium prices.This study underscores the importance of XAI in fostering trust and accountability in machine learning applications. By combining predictive accuracy with interpretability, the proposed framework has the potential to aid insurers in fair decision-making and enhance customer satisfaction through transparency in pricing.

DOI: https://doi.org/10.24321/3117.4809.202610