Description: Neural networks have fallen only to rise again twice. The latest incarnation borrows much from the past but adds elements to support deep learning. This article demonstrates the state of the art in deep neural network programming.

Description: While Model Efficiency and Model Governance may seem like completely separate topics, there is an intersection of them that should be of growing interest to modeling actuaries. This column from the Modeling Section Chair explores this area, asking how we will govern the increasing use of innovative modeling efficiency techniques.

Description: The article describes the key components of actuarial model, leading practices in designing them, and characteristics of well-built models.

Description: In this paper, we derive three important longevity Greeks on the basis of an extended version of the Lee-Carter model that incorporates stochastic volatility.

Description: This article discusses an upcoming SOA/CAS sponsored project regarding the Modeling of Economic Series Coordinated with Interest Rate Scenarios.

Description: Describes using the new multi-risk scenario generator to create sensitivity tests at moderately adverse probability levels, resulting in margins to use for PBR.

Description: An approach to quantify medical intervention savings when medical claims data is not available by leveraging overlapping measurement techniques.

Description: This paper applies GPUs and deep learning to achieve orders of magnitude performance improvement in the valuation of large portfolios of variable annuities.

Description: Looking for volunteer organizations to help Academy test new modeling techniques for PBR.

Description: This presentation introduces the Threshold Life Table as a solution to the problem of modeling mortality for extreme ages. This method is based on extreme value theory, and it avoids the need to extrapolate beyond an arbitrary age. This method produces an omega, the highest attainable age, without it being chosen arbitrarily.