MACHINE LEARNING DATA-DRIVEN LIFE INSURANCE PRODUCT LIFECYCLE MANAGEMENT USING REGRESSION AND ENSEMBLE LEARNING MODELS

Life Insurance Product Lifecycle Management (LIPLM) and Oracle InsurancePolicy Administration (OIPA) play a crucial role in ensuring the sustainability, profitability, and operational efficiency of life insurance offerings.This study provides a data-driven analytical framework for evaluating and improving life insurance product lifecycle performance using key operational and technical parameters.The analysis focuses on six critical variables: design cost, processing time, risk score, acquisition cost, IT performance, and lifecycle efficiency.Descriptive statistical analysis is used to understand the distribution and variability of lifecycle parameters, followed by correlation analysis to identify dependencies between the variables.To enhance predictive decision-making, linear regression and gradient boosting regression models are applied to forecast design cost performance.Model performance is evaluated using standard performance metrics such as R², RMSE, MAE, and explained variance.The results demonstrate strong relationships between cost, risk, and processing variables,Rao Gundala https://iaeme.com/Home/journal/IJITMIS 2