Date of Award

2024

Degree Type

Thesis

Degree Name

Master of Science in Statistics

Department

Computer Science and Statistics

First Advisor

Guangyu Zhu

Abstract

The report by the Insurance Information Institute underscores a notable increase in both claims frequency and severity, particularly highlighting a significant surge in accident claim severity within US car insurance from 2010 to 2019. Simultaneously, there has been a marked rise in the average expenditure on US car insurance during this timeframe. These shifts emphasize the critical need for accurate predictions to fine-tune premium adjustments and enhance the accessibility of car insurance coverage for a broader demographic of drivers. Consequently, numerous insurance companies are transitioning from traditional methodologies to incorporate machine learning (ML) techniques, providing a more sophisticated and reliable framework for generating outcomes. Nonetheless, the challenge persists in selecting the most optimal ML predictive model to effectively identify probable claims or potential premium defaulters. This study tackles these complexities by employing diverse classification methods and proposing specific techniques for feature selection and data resampling, with the overarching goal of constructing comprehensive classification models tailored for in-depth claim analysis.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.