Customer Lifetime Value Prediction of an Insurance Company using Regression Models

Banks are faced with the issue of evaluating who would be a better investment due to the unpredictability of the economy and the unexpected changes that occur in employment. The work that has been done and is shown in the study tries to address this issue and provide an effective machine learning model that can calculate the customer lifetime value taking into consideration a variety of different criteria. Customer Lifetime Value is a statistic that assists you in determining the amount of money that you are willing to spend in order to reach and acquire clients for your company. Utilizing techniques such as exploratory data analysis (EDA) and feature selection, the primary goal of this body of work in the field of research is to find significant and deciding variables for claim submission and approval within the framework of a learning environment. In order to identify which model provides the best level of accuracy, a number of different machine-learning algorithms have been tried and tested. Therefore, the model will determine the lifetime worth of a customer by first determining the components that are the most helpful and contributing, and then taking into consideration the model that has the highest level of accuracy.