By distinguishing risk more precisely, the updated model may help carriers expand eligibility without losing sight of mortality objectives.
RGA used deidentified insurance applicant data—Irix Prescription Data (Rx), Medical Data (Dx), and Credit Data (Cr)—to compare the performance of the Irix Risk Score 4.0 predictive model with Risk Score 3.0. The reinsurer also validated the new Credit Data-only model.
The new version proved significantly better at segmenting risk. The largest improvements in segmentation were seen in the 18–35 and 36–65 age bands. Scores correspond more accurately to the actual-to-expected (A-E) mortality ratios across all applicants, showing a significant improvement in the new model’s calibration to outcomes.
For carriers, better segmentation isn’t just a statistical improvement. It changes the risk decision itself. When risk can be distinguished more precisely, insurers can identify more applicants who fall within their target mortality thresholds while maintaining confidence in underwriting outcomes.
Key findings and conclusions:
- Risk Score 4.0 identifies significantly more insurable applicants below any mortality threshold. For example, at a cutoff corresponding to 50% cumulative mortality, Risk Score 4.0 qualifies 67% of applications, compared with 64% for Risk Score 3.0.
- Adding either Medical Data or Credit Data to the standard Prescription Data core model results in significantly improved performance. Unsurprisingly, the best results come from the model running all three datasets.
- Adding Credit Data improves mortality segmentation across all demographic groups.
- Risk Score results are durable. Even after 16 years, the model’s segmentation power remains evident.
RGA also found that cases flagged with the “AnyNicotine” indicator had a relative mortality slightly above 200%. Production clients running Risk Score 4.0 (Rx, Dx) see this flag in about 18% of cases.
The reinsurer’s analysis confirms that Risk Score 4.0 delivers more than improved model performance. By combining datasets, it enables more precise risk differentiation and helps carriers zero in on more insurable applicants at the same mortality thresholds. In a competitive market, that means better-informed, faster underwriting decisions and clear opportunities to write more business with confidence.
“Combining Prescription Data, Medical Data, and Credit Data consistently enhances mortality segmentation, with the most comprehensive scores delivering the strongest results.”
See how Risk Score 4.0 improves mortality segmentation, expand underwriting opportunity, and speed time-to-decision—read the full RGA validation report.
