Peggy’s areas of expertise include:
- Understanding statistics and machine learning, including generalized linear models, Bayesian models, survival models, decision trees, and clustering
- Performing data mining processes, including data preparation, feature extraction, model building, and model evaluation
- Developing risk scores with external data sources such as credit reports, vehicle characteristics, and telematics devices
- Pricing new insurance programs and redesigning existing ones by introducing advanced predictive modeling, tiering, and/or new rating variables
- Preparing rate filings to facilitate efficient regulatory reviews
Peggy has developed a variety of predictive models for profitability, claim risk, retention, and improving efficiency in underwriting and claims processes, including:
- Telematics: Developed telematics-based driving risk scores with both OBDII- and smartphone-based data
- Vehicle prediction model: Developed risk scores based on the characteristics of vehicles, such as horsepower, weight, and Electronic Stability Control
- Undisclosed driver pursuit: Identified policies most likely to have undisclosed youthful operators
- Driver training programs: Measured efficacy of various programs claiming to reduce crash risk for elderly and teen drivers
- Lifetime value modeling: Estimated the expected future economic value of a household, including potential value of future cross sales
- Mortality data mining: Mined hundreds of auto insurance variables for predictors of mortality risk
- Medical claim fraud: Modeled medical provider fraud using medical billing data
- Variable annuity lapse: Modeled policyholder behavior using policy and vendor data
Prior to joining Milliman, Peggy was Director of Analytics and Insights at the Allstate Research and Planning Center.
