Description: How well can we predict ACA HHS Risk Adjustment Data Validation (HRADV) results? Put another way, how susceptible is the current HRADV process to small sample volatility? What potential remedies are there to the current model's shortcomings? Every plan, regardless of how many members they have above the 1000 minimum, count equally if they qualify for an HRADV with how the result is interpreted, and the subsequent HRADV risk transfer ($330M in 2023).

Description: With the unprecedented proliferation in the size and complexity of data over the past decade, actuaries have invested considerable time and energy in the development of new skills and expertise in order to be able to understand and use “big data” to its fullest potential in the development of actuarial work product.

Description: Similar to how states had made adjustments to their capitation rates to reflect acuity adjustments caused by the onset of the pandemic, states will need to modify the rates to reflect the unwinding since utilization patterns and average acuity per enrolled member will change. When the continuous coverage requirements set forth by the COVID-19 Public Health Emergency (PHE) ended, Medicaid-managed care programs across the country adopted various approaches to phasing out maintenance of effort (MOE) as a result of changes to the PHE-era continuous eligibility requirements. Phasing out the MOE requirement will ultimately result in members who no longer meet eligibility requirements losing their Medicaid coverage. Further, states are facing a wide variety of circumstances and are implementing diverse approaches to the MOE phase-out. This topic will be of significant interest to all actuaries and stakeholders of the capitation rate development process for Medicaid-managed care programs. Join us as we discuss the operationalization of the PHE unwind while referencing the SOA's research project which models the effects of the unwinding on Medicaid eligibility and population costs. You will learn about the various approaches that different states have adopted to manage the unwinding process, which will be instrumental for accurately pricing managed care rates.

Description: At the conclusion of this session, attendees will be equipped to apply relative risk curves in their actuarial work, including the ability to examine dose-response relationships, apply population attributable fractions (PAFs), and develop customized risk models for cause-specific mortality and morbidity outcomes based on individual-level exposures to selected risk factors. These skills are becoming increasingly important as actuaries adopt novel applications of big data and dynamic health information to refine risk assessments and keep pace with global health trends.

Description: This session will explore governance considerations for insurance carriers leveraging machine learning models. During the session, panelists will share insights on the evolving predictive model and AI regulatory landscape, as well as techniques for developing or enhancing AI governance frameworks that comply with emerging regulatory guidance.

Description: Hear about some applications using quantile regression-derived individual and group claim distributions and how they may be used in various traditional health care modeling situations. The session will not focus on the technical use of quantile regression to obtain estimates of claim distributions, but more so is intended to focus on the uses of the distributions in actuarial modeling and the additive framework in assessing claims distributions. Presenters will show how actuaries can better assess risks by focusing on the individual- and group-specific claims distributions as opposed to traditional point-estimate-centric models.

Description: Over the last 10 years, Artificial Intelligence (AI) healthcare foundation models have made tremendous strides when it comes to delivering highly accurate predictive results when compared to traditional models. This is especially true for models developed and trained on the ‘language’ of healthcare. When trained on healthcare data sequences (claims, EHR, CPT, ICD, pharmacy, lab, etc.), these models deliver far more accurate results as to WHAT beneficiary-level health events will occur and even WHEN they will occur.

Description: How do social determinants of health (SDOH) affect health outcomes in the United States, how might SDOH factors be incorporated into financing and risk adjustment of Medicaid, and what implications might this have for market participants?

Description: Driver-based forecasting is a powerful tool to predict and estimate future outcomes. In recent years, driver-based forecasting has gained significant attention as a technique for actuaries to forecast the financial performance of insurance companies. Often there can be frustration around the ability to use forecasts to manage the business. However the objective of a driver-based forecast is to break down historic and projected movement based on the key drivers which impact the results. The key is to understand what the key drivers are on forecasts and what is the relative level of impact and influence we have on the drivers. Listen in on a discussion on the core principles of driver-based forecasting, including how to identify key drivers, collect accurate data, and leverage the latest technology to generate forecasts that traditional models can't match. Explore with us the various driver-based models and how actuaries can leverage them to enhance their decision-making capabilities. Then join the conversation about the challenges actuaries face when implementing this technique and how to mitigate these problems.

Description: As data continues to become more robust and readily available, there has been a push in the actuarial field to transition away from Excel to SQL and Python native cloud-based platforms. While these platforms are widely used and powerful, they present challenges for the actuarial industry: Requiring processes to be production-ready from the onset, technical expertise for integration and robust documentation. Low-code tools provide a unique alternative solution, which works when the organization's operating model allows for actuarial and IT to work together, giving actuaries the flexibility they need while maintaining a level of control followed by the organization In this session, you will watch demonstrations that showcase low-code tools and their use case in the actuarial space. See how these low-barrier-to-entry tools can be leveraged to create robust processes. We will discuss solutions such as Alteryx and Dataiku and how low-code tools can integrate with coding languages such as Python to create more robust processes.