Description: The Individual Life Experience Committee has completed their latest report on intercompany mortality experience by amount of insurance under standard individually underwritten issues. This includes study years 2009-2016.

Description: An application of GLM trees to mortality modeling using the Individual Life Experience Committee 2009-2015 dataset. GLM trees are a hybrid of GLMs and decision trees which are analogous to the way actuaries have analyzed data. The major benefits include speeding up actuarial analytic workflows, improving data understanding, and improving data visualization.

Description: As a life reinsurer, understanding mortality risk is mission critical. Superior models of mortality risk lead to more competitive pricing in profitable market segments and more efficient use of capital. Surprisingly, modern statistical tools such as predictive modeling have not previously been used to model mortality data to gain this edge. In this paper, we present the use of a predictive modeling technique called projection pursuit regression PPR to model mortality data. We first describe the process of creating a PPR model using inter-company mortality data collected by the Individual Life Experience Committee of the Society of Actuaries, and present the resulting model. We then discuss the process of using this model as a starting point for creating a more detailed PPR model of internal company mortality data.