Mortality prediction via age-specific band selection

Abstract

A novel mortality prediction framework, age-specific band selection, is proposed to borrow information from "neighboring" ages and train prediction models tailored for each individual age in a mortality table. This framework is further extended to borrow information across multiple populations through two proposed approaches: a distance-based approach and an ACF model-based approach. Extensive empirical studies with the Human Mortality Database are conducted to illustrate the enhanced prediction accuracy achieved by these methods.