Applying survival models to pensioner mortality data
Data from insurance portfolios and pension schemes lend themselves particularly well to the application of
survival models. In addition to the traditional actuarial risk-rating factors of age, gender and policy size, we
find that the use of geodemographic profiles based on postcode provide a major boost in explaining risk
variation. Geodemographic models can be better than models based on pension size in explaining socio-economic variation, but a model using both is usually better still. Models acknowledging heterogeneity tend to fit better than models which do not. Finally, bootstrapping techniques can be used to test the financial applicability of a model, while weighting the model fit can be used to address concentration risk.