Predicting High-Cost Members in the HCCI Database

• Activity Number: 382 - Novel Statistical Methodology for Insurance and Risk Management
• Type: Invited
• Date/Time: Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
• Sponsor: Section on Risk Analysis
• Author(s): Brian Hartman* and Rebecca Owen and Zoe Gibbs
• Companies: Brigham Young University and HCA Solutions and Brigham Young University
• Keywords: Health Insurance; Healthcare

Abstract

Using the Health Care Cost Institute data (approximately 47M members over 7 years) we examine which characteristics best predict and describe high-cost patients. We find that cost history, age, gender, and prescription drug coverage all predict high-costs, with cost history being the most predictive. We also compare the predictive accuracy of logistic regression to extreme gradient boosting.