Description: Uncertainty of a predictive model is a fact of life that many insurers could be overlooking at their peril without a framework for assessing it. The article provides a framework to understand the prediction uncertainty, which can be critical for the insurance operations using predictive models. Coin toss example explains model uncertainty and randomness inherent in making predictions to the number of heads expected. A mortality analysis case study illustrates how the Bayesian methodology can be used to develop the prediction uncertainty. In particular, the article shows that the Bayesian framework is a way to combine historical data and actuarial judgment, and directly address the model uncertainty through its posterior distribution.

Description: The most recent demographic data published in Mexico allows us to analyse in detail the profound demographic transition that has been taking place in the country for more than four decades. It is possible to develop forecasts for the future on the basis of this historic experience. The purpose of this article is not only to illustrate the profound demographic change in Mexico – and what it is expected to experience over the coming decades – but to highlight the challenges for the insurance industry posed by the various demographic trends. Wherever challenges are found, however, opportunities also exist, provided the industry succeeds in adequately transforming its own processes and meeting the needs of a changing market.

Description: Deep learning neural network applied to experience analysis for post-level term lapse and mortality.

Description: An application of GLM trees to mortality modeling using the Individual Life Experience Committee 2009-2015 dataset. GLM trees are a hybrid of GLMs and decision trees which are analogous to the way actuaries have analyzed data. The major benefits include speeding up actuarial analytic workflows, improving data understanding, and improving data visualization.