<![CDATA[To help insurers determine insurance rates incorporating maternity factors, it is crucial to understand the maternity recovery rate, which was a metric used by insurance companies to understand how much of the expenses associated with maternity care and related medical services are covered by their policies. This paper employed Extreme Gradient Boosting (XGBoost), a powerful method for handling complex data relationships and preventing overfitting, on North American Group Long-Term Disability dataset obtained from the Society of Actuaries, which listed maternity as one of its categories, to predict the maternity recovery rate. In comparison, other machine learning methods such as Gradient Boosting Machine (GBM) and Bayesian Additive Regression Tree (BART) were used, with Root Mean Squared Error (RMSE) values calculated the difference between predicted and observed maternity recovery rates. Four datasets, 3 imbalanced and 1 fairly-balanced, were created out of the original dataset to test each method’s predictive prowess. The study revealed that XGBoost performed exceptionally well on the imbalanced datasets, while BART showed slight superiority in fairly-balanced data. Furthermore, the model identified the duration, exposures, and age of participants in both predicting maternity recovery rates and the underwriting process. ]]>
Copyrights © 2023
