Description: Describes what a Delphi study is and why actuaries might want to use one.

Description: A summary of how the Forecasting and Futurism Section is networking with other SOA sections and with external organizations to collaborate on various projects. Also highlights new events and projects happening on the forecasting and futurism front.

Description: The author discusses the use of genetic algorithms as they apply to actuaries, specifically the application of characteristics and their potential to solve life insurance asset and liability management problems. He also highlights various ways genetic algorithms can be used to solve a variety of actuarial problems.

Description: An introduction to Hidden Markov Models, which are used extensively in speech and facial recognition technology. They are a useful tool in forecasting time series and in developing categorizations of data based on the values of the data themselves.

Description: A general introduction about predictive modeling in insurance applications. Some basic models are discussed, such as Generalized Linear Model(GLM), Calssification and Regression Tree Model. Other models are also briefly introduced, including data clustering, neural networks and support vector machine.

Description: Identifies current trends and considerations when setting the mortality improvement assumption for individual life insurance in the US.

Description: The comments of DxCG about their participation in the SOA study A Comparative Analysis of Claims-Based Tools for Health Risk Assessment.

Description: The article provides a high-level, non-technical, introduction to artificial neural networks (ANNs) and deep learning with an application to risk management. The method relies on typical ANN components such as nodes, activation functions, and optimization through gradient descent.

Description: The article gives a brief history of the development of the Delphi method, and describes the use of the Delphi method in studies by the Society of Actuaries over the past 25 years.

Description: Even the best algorithms are only effective if they are trained on appropriate data. This article discusses common pitfalls in creating a training data set.