Medical Insurance Predictive Modelling: An Analysis of Machine Learning Methods

Predicting healthcare expenses accurately is crucial for a wide range of stakeholders and healthcare institutions. The healthcare industry generates massive volumes of data about patients, symptoms, and diagnoses, but this data has yet to be thoroughly studied to provide insight into patient healthcare costs. Machine learning (ML) may help enhance policy wording efficiency in the insurance industry, and ML algorithms are especially beneficial in healthcare for projecting high-cost, high-need patient bills. A computational intelligence technique is used to estimate healthcare insurance expenditures using machine learning algorithms. It is difficult to choose a single regression model for predicting health-care costs, thus we build an algorithm that uses multiple regression models and calculates the accuracy. The stochastic gradient boosting technique achieves an accuracy of 88.98%.