Life Insurance Ownership Prediction Using Machine Learning Approach

Customer profiling has become one of the essential marketing strategies for any business, such as the insurance market, to identify potential policyholders and bankers to identify potential defaulters. One well-known method of carrying out customer profiling and segmenting is machine learning. Hence, this study aims to provide a helpful framework for predicting potential life insurance policyholders using a data mining approach with different sampling methods and models. Various sampling (SMOTE and RUS) and ensemble (bagging and boosting) techniques are proposed to handle the imbalanced dataset. The result revealed that the Logistic Regression outperformed other models in most of the evaluation criteria, and in this imbalanced dataset, the ensemble models do not guarantee high performance. However, the ensembled and sampling method plays a significant role in overcoming the imbalanced problem