Description: Actuaries are leveraging predictive modeling and machine learning more and more as they strive to provide greater value to their stakeholders. Actuarial standards of practice provide guidance around modeling and data. The world has changed significantly over the last few years, so it is important these models be tested for fairness as well as any statistical biases. This article addresses some of the key issues actuaries need to be aware of as Corporations and society work through the responsible us of this technology and underlying data.

Description: The objective of this paper is to provide a practical guide with concrete case studies to help actuaries implement artificial intelligence and machine learning (AIML) to help accelerate the speed of analysis for life and annuity actuarial modeling. We do so by researching the existing literature regarding AIML and its applicability to stochastic modeling and exploring case studies.

Description: This e-course will introduce you to a set of advanced business analytic techniques. We define advanced business analytics as a set of tools and techniques to assist in key business decisions.

Description: This report provides actuaries and other professionals working with risk, data and analytics or program evaluation in the health care space with considerations and frameworks related to the use of determinants of health (DOH) in data and actuarial work streams. Such frameworks can leverage new data sources to enrich health care data analysis to move beyond traditional data elements, such as age, gender, zip code or health diagnosis.

Description: "Risk adjustment is an important aspect of establishing appropriate capitation rates. When a set of services is carved out for specific management under a sub-capitation, establishing appropriate adjustments for varying levels of underlying risk is more complicated. Dive into analytical and operational challenges and resolutions as presenters share more about developing a risk adjustment model specific to the carve-out of behavioral health services through a real-life case study. You will further explore a definition of the use case, availability of historical data sets, selection of the modeling approach, learnings from the iterative modeling process, and the potential application of the results. After attending this session, you will be able to: Understand why a behavioral health specific-risk adjustment model has business value Understand the unique challenges related to developing risk adjustment on member and cost subsegments Understand the impact of trade-offs between model complexity and interpretability in the context of implementation Increase awareness of data nuances and requirements unique to this type of project Describe analytic techniques that can be investigated for use in projects of similar business objectives"

Description: The Delphi method is a non-quantitative forecasting approach that is most useful when other forecasting techniques appear to have limited value. The Society of Actuaries (SOA) has had some impressive results from Delphi studies (even quoted in the Wall Street Journal for their uncanny accuracy on long-range predictions). Attend this session to learn about this effective, yet underutilized method of leveraging the wisdom of crowds.

Description: Almost half of recent FDA approvals have been for orphan drugs. This trend is expected to continue in 2023. Orphan drugs are priced more than 30 times higher than non-orphan drugs, therefore their cost burden in aggregate has the potential to overwhelm the budgets of payers, especially that of smaller health plans. Hear how the cost impact analysis for smaller health plans require different considerations than for a larger health plan when modeling the impact of rare diseases.

Description: This year’s Life Meeting was unable to take place in person as planned in New York City. We are looking forward to the Life Meeting returning to New York City in 2024!

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.

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.