Clustering Application for Data-Driven Prediction of Health Insurance Premiums for People of Different Ages

A health insurance premium is a monthly fee that is paid in a health plan to typically pay for medical, surgical, prescription drug and sometimes dental expenses incurred by the insured. Since 2010, the affordable care act has prohibited insurance companies from denying coverage to patients with pre-existing conditions and has allowed children to remain on their parents' insurance plans until they reached the age of 26. Creating the policy is a really important and challenging task. In order to determine health insurance premium quotes, there are several factors that have to be taken into consideration when defining a premium, such as pre-existing diseases, age, gender, family medical history, lifestyle, etc. In this paper, a combination of the K-means algorithm and the Elbow method is developed to accurately group people in an optimal number of clusters based on similarity. Based on this evaluation, the health insurance premium quote via the provided factors to predict the range of the health insurance premium quote for each group of people. Keywords - k-means technique, Elbow technique, clustering technique, data mining, health insurance.