Machine-Learning Methods for Insurance Applications-A Survey

The Society of Actuaries is pleased to make available a research report that provides a literature survey of methodologies applying machine learning to insurance claim modeling. Summaries of data and empirical work can be found in the two accompanying Jupyter files. The report was authored by Alex Diana, Jim Griffin, Jaideep Oberoi, and Ji Yao.

Material

Machine-Learning Methods for Insurance Applications

Group Long-Term Disability Jupyter File

Long-Term Care Jupyter File

Group Long-Term Disability Data Set Comparison

Long-Term Care Data Set Comparison

Thank You

The SOA would like to thank the following individuals for serving on the Project Oversight Group:

Syed Danish Ali
Mary Pat Campbell
Thomas Farmer
Valerie Gingras
Lie Jen Houng
Min Mercer
Michael Niemerg
Shisheng Qian
Jim Wright, SOA Project Manager
Mervyn Kopinsky, SOA Experience Studies Actuary
Steve Siegel, SOA Research Actuary
Ronora Stryker, SOA Research Actuary
Barbara Scott, Sr. Research Administrator

If you have comments or questions, please send an email to research@soa.org.