Description: Machine learning models are not black-boxes; these models can easily be interpreted using tools like SHAP, LIME and Anchor. These tools can facilitate the understanding of the model and the business problem. We can used these tools to build better models and communicate how predictions are generated. This article demonstrates their use in a mortality model.

Description: A description of the random generalized linear model (RGLM) and how to use it.

Description: The Delphi Method is discussed in detail. The method attempts to filter out the consensus bias that can result from societal forces by employing a technique whereby an anonymous collection of opinions is used, supplemented by feedback loops that can be used to influence outcomes.

Description: This article provides a brief introduction to forecasting methods that are potentially relevant to actuarial work.

Description: This article compares three potential approaches to determining new coefficients for health-based risk scoring models: full recalibration, p-value credibility weighting, and penalized ridge regression.

Description: In this article we examine the benefits and drawbacks of using a global surrogate of a black-box model. Are surrogates a comfortable middle ground that provide insurers high predictive power as well as model explainability?

Description: Impact investing is investments in “companies, organizations and funds with the intention to generate social impact alongside a financial return”.

Description: This article describes the use of artificial society modeling to gauge the effect of insurance agent population and effectiveness on individual life insurance sales. This is part of an ongoing effort to extend the use of one type of agent-based modeling beyond health care, but is far from a practical application at this point.

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: Specifies 6 rules which help shape not only good crime-scene analysis, but good futures practice, as well. These rules address project management and control.