Description: An introductory article describing how Bayesian statistics has evolved over the past 20 years and why it offers the actuarial discipline powerful tools to better understand and manage risk. Compared with traditional (frequentist) and black-box (machine learning) approaches, Bayesian analysis provides explainable models focused on distributions of estimates instad of simply point estimates.

Description: This session is an in-depth interview of two actuaries turned Artificial Intelligence (AI) experts. We aim to have a conversation that gleans into each of their journeys and what led them to the path they are now on. We will open up the last ten minutes for audience questions. At the conclusion of this session, attendees will know Eric and Joe much better, have an understanding of what AI/machine learning/data scientist work is like for actuaries, and, for those who are curious to get more involved with AI, some encouragement to pursue their interests.

Description: Session 2F: Artificial Intelligence and Actuarial Modeling - Ask an Expert!

Description: Session 7B: Health AI in Practice - Lessons From Top U.S. Health Systems

Description: Session 10F: Debating AI - Valuable Tool or Overhyped Trend?

Description: David Moore has seen life insurance industry disrupted by new technology. David’s company seeks innovative approaches to engage with customers using analytics.

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: Mining Electronic Health Records using a Natural Language Processor.

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: Second article in a series on how to use predictive analytics to improve the development of long-term care projection assumptions.