U.S. Post-Level Term Lapse and Mortality Predictive Modeling
Authors
Aisling Bradfield, FSAI
Julien Tomas, PhD
Joanne Yang
Description
This report provides an educational background on the process of building predictive models, as well as a detailed presentation of the model results. Predictive models provide a method to capture variation by multiple variables and understand the relationship between these variables. This allows for a deeper understanding of key variables than is possible under a traditional approach.
Report
U.S. Post-Level Term Lapse and Mortality Predictive Modeling
Data Visualizations
These interactive dashboards are visualizations of key metrics found in the report. They provide filtering, drill-down, and other interactive capabilities that allow you to focus on specific subsets of the data.
Tableau dashboards - Shock Lapse
Tableau dashboards - Mortality
Acknowledgments
The researchers would like to express our gratitude to all the participating companies for making this project possible. Your contributions have led to a new industry benchmark of experience results and predictive modeling for shock lapse and post-level term lapse and mortality experience. We would like to thank the SOA, along with their staff, for their guidance and support on this research project.
At the Society of Actuaries:
Korrel Crawford
Cynthia MacDonald, FSA, MAAA
Mervyn Kopinsky, FSA, EA, MAAA
Ritesh Patel
The researchers’ deepest gratitude goes to the following members of the Project Oversight Group (POG) for their diligent work overseeing the data request development, discussing data and predictive modeling results, and reviewing and editing this report for accuracy and relevance. Project Oversight Group members:
Brian Carteaux, FSA, MAAA [Chair]
Michael Niemerg, FSA, MAAA
Larry Bruning, FSA, MAAA
Tony Phipps, FSA, MAAA
Brian Holland, FSA, MAAA
Mark Rosa, ASA, MAAA
Donna Megregian, FSA, MAAA
Mary Simmons, FSA, MAAA
Questions or Comments?
Give us your feedback! Take a short survey on this report. Take Survey
If you have comments or questions, please send an email to research@soa.org.