Description: While the major market crash subsequent to the widespread contagion of the COVID-19 virus was readily predictable, the rapid recovery and ongoing growth subsequent to it was not. Market dynamics around the recovery resist characterization by most traditional analytical approaches. In examining the circumstances around the emergence of a large retail class of investors, one sees that ingrained human tendencies, particularly optimism bias, have fueled much investor behavior responsible for the recovery. Understanding this makes it possible to predict potential future crashes and develop behavioral interventions for subsequent market recoveries.

Description: This article summarizes key points from the recently published research paper “Deep Learning for Liability-Driven Investment,” which applies reinforcement learning and deep learning techniques to liability-driven investment (LDI).

Description: The paper demonstrates that the most popular rationalization for evolving glide paths is flawed and should be discarded. The paper also demonstrates that glide paths should generally evolve for investors that endeavor to optimize outcomes and reevaluate their portfolios regularly.

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: Discussion of the new scenario generator selected by the NAIC and its behavior at low interest rates.