Description: This article discusses data mining and the statistics of coincidence, and provides “guidelines for backtesting integrity” to help ensure results have value beyond mere coincidence. Editor’s Note: The following article originally appeared in the Winter 1998 issue of the Horizon, a publication of BARRA, Inc., and is reprinted with permission.

Description: The article warns against treating the results of a stochastic model with more deference than other actuarial analysis, and describes some hidden risks involved with choice of model and calibration.

Description: A look at the COVID-19 crisis in 2020, and how it differs from both prior financial crises and pandemics. The COVID-19 pandemic gives actuaries an opportunity to assess different ways risk may interact, and thereby adjust the profession’s work for the future.

Description: There are two main techniques for evaluating the financial impact of interest rate movements on insurance companies: duration measures and computer simulations. In many ways these approaches provide complementary viewpoints.

Description: Are Your Scenarios on Target?From Risks and Rewards Newsletter, August 2005, Issue No. 47. Actuaries are faced with the dilemma of how to incorporate advances in insurance products and modeling technology into their work. Increasingly, this means looking at a large number of potential outcomes using stochastic simulations.

Description: This article discusses facts and issues related to the selection of a stock’s price distribution.

Description: “It’s interesting to note that, given the past year’s reversal of fortunes in the stock markets, all the media rap about heated inquiries around back-dating options has stopped.”

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: The article discusses that drawbacks of the HJM Heath-Jarrow-Morton class of stochastic interest models and suggests the use of the Longstaff-Schwartz string model. It describes the use and benefits of the Lonstaff-Schwartz string model.

Description: In this article about interest rate models, the author develops an empirical description of the term “interest rate regime,” and looks at the relationship between changes in yield curves and moving to a new interest rate regime.