Description: Many life and health insurers are beginning to use Predictive Analytics (PA) for a variety of purposes. This article addresses the unique challenges and potential disruption PA brings to the risk manager, as well as the opportunities.

Description: Health claims are not normally distributed. Claims Forecasting can be improved by understanding the entire distribution of plausible values of future claims, for example knowing there is an 80% chance future claims are between $340 and $375 PMPM. Confidence intervals around our estimates allow us to understand for each range around the best estimate (for example +/- 1%) what is the probability that future claims will fall in that range. Quantile Regression is a mathematical technique where you can estimate any percentile of the claims distribution you are looking for as a function of demographics, diagnosis indicators, prior cost variables, or other significant predictors. You can see which coefficients are important at different parts of the distribution. Individual and group distributions can be constructed. There are numerous applications in pricing and underwriting, stop loss, provider profiling, ACO target setting, allocation of group risk charges based on volatility, discounting strategy, and experience analysis.

Description: Process of building a predictive model and related considerations.

Description: This article is a basic introduction to information theory with the goal of explaining the maximal information coefficient.

Description: This paper describes techniques that can be used to access any specific piece of information in Wikipedia, such as medical information.

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: In How Significant Is Statistical Significance? The author discusses the p-value that is often used to determine significance. Sometimes we place too much reliance upon canned metrics and lose the ability to notice when something is mathematically sound but not sensible. The article provides three simple examples that require no complicated mathematics to follow yet provide a basis for some deep thought about statistical significance versus substantive significance.

Description: Mining Electronic Health Records using a Natural Language Processor.

Description: The article explores a closed-form forecasting method that combines Exponentially Weighted Moving Average (EWMA), weighted linear regression, and ridge regression (L2 regularization). The approach addresses two key challenges in time-series forecasting: adapting to nonstationarity and mitigating overfitting due to multicollinearity. EWMA assigns more weight to recent observations, while ridge regression penalizes large coefficients to stabilize estimates. A cross-validation strategy across rolling time windows selects optimal hyperparameters: the EWMA decay factor (α) and the ridge penalty (λ). The method is tested using repeated regressions of stock returns, showing that most hyperparameter combinations outperform ordinary least squares (OLS) under the (λ=1, α=0) setting.