From Life Expectancy at Birth to Life Table. A Novel Approach

Andrea Nigri, Sapienza, University of Rome
Susanna Levantesi , Sapienza University of Rome

The shape of Life expectancy has always caught the researchers'interest. From the beginning of the new millennium, its evolution has led scholars to give more emphasis to life expectancy investigation. Following this line of research, we propose a novel model, based on Deep Neural Network (DNN) in order to provide unobserved mortality rates (or more general vital rates) using demographic summary measures. The present analysis has been carried out by using life expectancy at age 0 and 65 as input for years Yi. Thus, as output, we obtain mortality surface for the same years

See paper

 Presented in Session P3. Poster Session Migration, Economics, Environment, Methods, History and Policy