Using Artificial Neural Networks to Predict One Year Population Mortality Rates

Sammanfattning: Being able to predict mortality rates is the key factor in any pension or life insurance companies’ business model. Artificial Neural Networks are already being tested and implemented to predict mortality in the field of medical science, with recent studies showing promising results of their predictive power in one year mortality rates. Today, insurance companies in Sweden utilizes the Makeham curve to model and approximate mortality, traditionally with only age and sex being its input features. This study utilized artificial neural networks to model one year mortality rates that could otherwise be derived from the Makeham curve. Features other than sex and age were also included as a part of this study to introduce more features that could affect mortality rate. The network was successful at modelling the one year mortality rates and it was able to distinguish between age, sex and the newly introduced features. It yielded results that were on par with predictions made by the Swedish branch organization of the private insurance companies.