Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Actuarial, Finance, and Risk Managment
Elisabeth Gloria Manurung
Unknown Affiliation
Economics, Econometrics & Finance Mathematics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparison Between Machine Learning Regression Modelling to Predict Individual Premium Price Srava Chrisdes Antoro; Elisabeth Gloria Manurung; essykapna Randalline; Maria Yus Trinity Irsan
Journal of Actuarial, Finance, and Risk Management Vol 2, No 2 (2023)
Publisher : Journal of Actuarial, Finance, and Risk Management

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33021/jafrm.v2i2.4807

Abstract

Machine Learning (ML) applications in healthcare aim to simplify people's lives by swiftly predicting and diagnosing diseases, outpacing the capabilities of most medical experts. A direct connection is established when technology, particularly digital health insurance, is employed to minimize the gap between insurance providers and policyholders. This has significantly transformed the way insurers create health insurance policies and has led to faster service delivery for consumers. Machine learning is utilized by insurance companies to offer clients precise, prompt, and efficient health insurance coverage. In this study, a regression method was trained and assessed to which one gets the bigger accuracy to forecast premium prices. The researchers accurately predicted the premium prices individuals incur based on various factors, such as age, diabetes, blood pressure issues, height, and weight. The experimental outcomes revealed the best method to predict is the KNN method in the data set that was used in the analysis, with an impressive accuracy of 87.73%. In comparison, the Random Forest is 87%, and the Boosting is 87.19% and the authors analyzed the model's performance using key metrics to assess its effectiveness. 
Co-Authors essykapna Randalline Maria Yus Trinity Irsan Srava Chrisdes Antoro