Description: Discussion on modeling Medicare Supplement insurance and the considerations when choosing an Actuarial Modeling Software (AMS). Focuses on model risk management, key modeling assumptions and inputs, and the complex interactions between modeling assumptions and why its critical to have a model that can handle that complexity. This article also touches on the incorporation the of accounting and regulatory regimes into the model, including Statutory, GAAP (Legacy and LDTI), and Tax regimes, and the modeling considerations for sensitivity testing and capital planning. Lastly, the article highlights the capabilities to look for when choosing an AMS for Medicare Supplement

Description: Read the November 2019 issue of The Modeling Platform, published by the Modeling Section. Newsletters provide practical information for the working actuary, articles on trends that impact sections and news about section activities.

Description: According to the Actuarial Standards Board’s Actuarial Standard of Practice No. 49 (ASOP 49), actuarially sound Medicaid managed care capitation rates will include a provision for underwriting gain in order to provide compensation for the risks assumed by an MCO. However, there is no generally accepted method for quantifying underwriting gain in managed Medicaid capitation rates. This article discusses a new model developed to address this void and calculate underwriting gain. The model was developed by researching existing financial literature and performing a statistical analysis of industry data to build out a framework that can be leveraged to estimate underwriting gain.

Description: This paper reviews the general methodology of capture-recapture procedures and describes some applications such as estimating the size of the undercount in censuses and estimating the number of duplicate records on in a database. From Actuarial Research Clearing House 2006.

Description: This article discusses the advantages, logistical concerns, and pricing formulas of implementing a TNHP, in which members pay less for treatment from providers who meet higher quality and cost-effectiveness standards.

Description: "Explore a general introduction to the opportunity of applying a relatively newer area in machine learning called uplift modeling, which has been successfully used in retail (Wayfair etc). The concepts are parallel to the intervention programs in health care, where we are interested in measuring the treatment effects and ultimately directing the right members to the most effective programs, driving the highest value for the programs both from a financial and health outcomes perspective. Uplift modeling can also be viewed in context of causal modeling where we are interested in assigning cause to a treatment relative to a member not receiving the treatment. Check out an introduction on the concept, seehow it relates and builds on existing work, and use a demo to showcase the potential of integrating this ML approach to current work."

Description: 2003 Valuation Actuary Symposium, San Diego, CA. In this Teaching Session the instructor discussed the importance of making sure the correct inferences were drawn from stochastic testing exercises. Topics included: 1. Applying the assumption of a normal distribution. 2. Drawing inferences about, and creating confidence intervals around, a population mean. 3. Drawing inferences about, and creating confidence intervals around, tail percentiles. 4. Certifying anticipated mortality under XXX in a mathematically concise way.

Description: The Introduction to Modeling: Summer Boot Camp series provides an overview of modeling topics and techniques aimed at the beginner modeler. This interactive series is comprised of five 90-minute sessions with opportunities to discuss the topics in small break-out groups.

Description: In this presentation, actuaries and data scientists from Cleveland Clinic and Milliman discuss the development of a sepsis prediction model using machine learning. Presented with a unique challenge of handling massive amounts of data for near real-time risk scoring, the team took their model development to the cloud and delivered a product in less than a week through a unique virtual engagement.