Speaker(s): Frank Schiller (Munich Re)
Own occupation disability income protection insurance (henceforth: DI)  is a complex product with a dependence on various individual, socio-economic and medical risk factors. Our experience analysis is based on more than 30 variables that are derived from application, inforce and claims data and are augmented by external data sources and covers a considerable share of the German DI market. Traditional methods – which compute rates for risk factors separately on sub-portfolios – often become unstable or inconsistent in such a high-dimensional setting.
Therefore we apply several multivariate data analytic methods to predict German DI incidence rates. We compare these different methods and share some of the results and their application in product design and pricing or process design for UW and claims. For these applications a careful interpretation and validation by market experts and medical doctors is crucial.