Description: A review of the Johns Hopkins Data Science Specialization courses with special emphasis on how they may be useful to actuaries.

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: Python is the leading programming language for data science. Python programming is one skill that actuaries should acquire. It facilitates analytic work, and the available visualization tools help to communicate ideas. In this article, I use a traditional actuarial problem, mortality modeling, as an example.

Description: While many know that machine learning is a big deal and even have a general idea of what it is, many do not know what machine learning can do for them. As an alternative to citing achievements or explaining algorithms, this article outlines the challenges that occur in statistics and the solutions that machine learning offers. Some of those challenges include correlated predictors, missing data, data interaction, and prediction intervals. Corresponding solutions include regularization technics, missing value imputation with KNN, tree based models, and cluster analysis for backtesting.

Description: Regression to the mean is a phenomenon that arises when comparing sequential data points. It states that when an initial observation is extreme or an outlier, future observations will be closer to the average. Health care actuaries need to understand and be able to mitigate the effects of regression to the mean to avoid misapplying predictive models or misstating measurements of historical effects.

Description: Traditional risk scoring models include only fixed (non-random) demographic and condition-based variables. By including the provider effect as part of the risk scoring model as a random effect, we can get better estimates of provider performance (incorporating practice patterns conditional on patient morbidity profile). This approach can be generalized to study other factors that are now masked in error variance (i.e. area, Social Determinants) but if modeled could give us better estimates of risk