NORMA eResearch @NCI Library

Identification and Prediction of Factors Impact America Health Insurance Premium

Sun, Jun Jun (2020) Identification and Prediction of Factors Impact America Health Insurance Premium. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (4MB) | Preview


For insurance companies understand the factors that impact user’s health insurance premium would be very essential to make the accurate charge, premium always be a user’s priority consideration to make appropriate decisions. This project used predictive analytics and insurer attributes to identify the factors that influence health insurance cost, according to the output which demonstrated the majority factors that contribute to health insurance premiums cost are BMI, smoke status, age and children, these four factors have significant correlation impact to health insurance premiums. Through discovery the correlation between individual’s attributes, utilized 3 regression models and 1 statistical model to solve the research question and provide meaningful insights for insurance companies, and used another seven classification models to resolve the sub research question. The comparison and evaluation of several model outputs that determine the most effective and best performance model implemented to achieve the research question is Random Forest model with 80% R square value, Support Vector Machine is a second performance model with 67% accuracy. Also, SVM and Random Forest used to solve research question and sub research question.
Key Words: Machine Learning models, Predictive Analytics, Insurance Premiums, Rsquare value, Accuracy.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 18 Jan 2021 15:06
Last Modified: 18 Jan 2021 15:06

Actions (login required)

View Item View Item