CASE STUDY
Claim Sense: Early Claim Forecasting Model
BUSINESS PROBLEM
- Create an early claims forecasting system for a Life Insurance Company to enhance the efficiency of anticipating and managing claims across all products. Utilize data from multiple sources to improve the performance of the current underwriting process.
PERFORMANCE
Model Results
MODEL NAME | CAPTURE RATE IN TOP 5 PERCENTILE |
TERM Product 1 YEAR CLAIM | 39.53% |
TERM Product 1 YEAR VOID | 60.96% |
HYBRID Product 1 YEAR CLAIM | 42.86% |
HYBRID Product 1 YEAR VOID | 49.23% |
TERM Product 3 YEAR CLAIM | 34.63% |
SOLUTION
- Multi-stage ML model to improve decisioning on customer journey process.
- Stage -1- claim based on Application profile data.
- Stage 2 – claim based on Profile, IIB data with Medical data.
- Another model was developed to classify manual void to minimize void process in future
- Segmented model were built to take care the loss,1 Year vs. Multi year.
- Hyper parameter Optimization: Iterative Experimentation with multiple Machine Learning Algorithms and Framework.
BENEFITS
- Risk Segmentation of Applications in the Customer Journey.
- Optimization of Due Diligence Efforts.
- Enabling Instruments of Differential Pricing based on data and history.
- Automated Underwiring to minimize human intervention, easy to scale on demand. Expected Claim Reduction by 25%.
Performance measurement of Model at various thresholds - ROC curve
