Description: Back in the day, when data was scarce and computers were slow, actuaries were forced to use simple methods to account for risk. By far, the most common method was to add a margin, usually 5% to a “best estimate” calculation. Remarkedly, this method still works quite well in the aggregate. The problem is that, in many cases, decisions today require a more in-depth analysis. For example, how big a risk is a health plan really taking if it lowers its premiums by 10% to attract more members? This session will discuss techniques for measuring risk in today’s environment. Speakers will also share the results from the 5/50 research project, which forms the foundation for the techniques.

Description: Stochastic modeling requirements are resulting in more 'run time' and less 'analysis time'. An expensive solution is leveraging cloud infrastructures and robust computing grids. The presenters will explore the use of cluster modeling and present case studies showcasing this automatable and robust technique, which could allow actuaries to recover the time lost to 'run time'. Developing automatable and clustered models requires robust governance practices to ensure credibility of results.

Description: Actuarial models and modeling processes continue to grow in complexity, accelerated by the changes in U.S. Statutory, U.S. GAAP and IFRS reporting requirements in the past few years. Modeling and valuation teams are expanding their toolkits beyond the traditional vendor-maintained actuarial software and the MS Office suite of tools. Companies have started to use a variety of tools to improve model dev and valuation processes, including: - Data management - Automation and workflow - Reporting and analytics

Description: There is value in a framework that allows a smooth transition from a qualitative assessment to a quantitative analysis as entities mature in their understanding of climate risk. In this webcast, a case study on climate change's impact on home prices, a topic the SOA published research on, will be discussed along with other perspectives. The goal of this webcast will be for attendees to takeaway knowledge and tools to begin to move toward quantitative assessments in their own fields of practice.

Description: 2021 Life Meeting - Session 5E: Importance of Strategic Asset Allocation in a Rapidly Changing Macro Environment 8.31.21 Recording

Description: Dedicated to those interested in the approaches of long-term pension assets, the How Should Long-Term Pension Assets Be Invested? A Debate webcast allows you to focus on where to devote your pension attention. Participants in this panel concentrate on perspectives and opinions on the direction of long-term pension assets. Expand your viewpoint on the investment of long-term pension assets by discovering other ideas about the industry. Determine how to handle your association with these assets and how to make the best move for the retirement business.

Description: This webcast will detail interpretable machine learning techniques for participants to gain an intuition and understanding about the use of these techniques. We will discuss how to apply them, how to understand them, and how to avoid potential pitfalls.

Description: Analyzing large quantities of raw complex data is often a challenge in the health care industry. During this webcast, there will be a demonstration of how unsupervised machine learning techniques can be applied to such data to help bring useful insights. This will include examples that use unsupervised learning techniques spanning dimensionality reduction, clustering and anomaly detection.

Description: 2021 Life Meeting - Session 8D: Three Years After Model Conversion: How’s it Going? 9.1.21 Recording

Description: Historically different approaches have been used by actuaries in modeling mortality improvement. The SOA has recently released a framework that practitioners can use to project mortality improvement, providing methodological consistency across a range of applications.