PlumX Metrics
Embed PlumX Metrics

Enhanced Maximum Likelihood Models for Underreported Variables: Extending to Multiple Claims Dimension

2023
  • 0
    Citations
  • 31
    Usage
  • 0
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Thesis / Dissertation Description

This thesis builds upon the foundations laid out in Xia et al. [2023], which explored the utilizationof Maximum Likelihood approach to model misrepresentation data in Generalized Linear Models (GLM) ratemaking models. We introduce the concept of “underreported variables”, a form of insurance misrepresentation where insured individuals provide inaccurate information about risk factors that influence insurance eligibility, premiums, and insured amounts. Unlike fraudulent misrepresentation, underreported variables arise from a lack of awareness regarding the insured’s mental and physical health conditions, rather than fraudulent intent. The study rigorously tests the proposed model using health insurance data and extends its applicability to other insurance domains such as auto and home insurance. This research enhances claim prediction models by incorporating the probability of underreported variables, improving the accuracy of predictions. The work builds on earlier research by employing the Maximum Likelihood method for modeling and estimation, specifically in scenarios where each policy may have multiple claims. It derives partial and complete log likelihood functions for ratemaking models and uses the Expectation Maximization (EM) algorithm for parameter estimation. Notably, this research aligns with broader efforts in the insurance industry to detect fraudulent claims. It also contributes to the understanding of underreported variables in insurance ratemaking models, offering insights into improving predictive models for insurance claims across various domains.

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know