Description: Can you answer the question, 'What are the chances we will lose more than $1 million?' without saying, 'It depends'? If you miss a projection, can you estimate the chances that the miss was due to random variation versus an incorrect projection? Listen in as presenters demonstrate how to answer these questions and others using total risk analysis. Total risk analysis includes quantifying both the random variation risk and the projection risk associated with actuarial functions like pricing and reserving. After attending this session, you will be able to describe total risk analysis and to apply to many health actuarial functions.

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: Risk adjustment is widely used by public and private payers in value-based contracting and other risk-sharing arrangements aimed at addressing population health. Addressing social determinants of health (SDOH) and improving equitable outcomes is one of the aims of population health. Could SDOH be incorporated into risk adjustment? If so, how and how effectively? What implications might this have for market participants? In this session, Joan Barret, FSA, MAAA, from Axene Health Partners will begin by presenting background and findings from the 2022 SOA research report 'How Does Where you Live Impact Your Health?.' This is a question addressed through deep literature review and quantitative analysis, followed by an exploration of strategic approaches and barriers for payers and providers that wish to address SDOH inequities. Then, Rong Yi, FSA, MAAA, and Jeff Milton-Hall, FSA, MAAA, from Milliman will present their new SOA-sponsored analysis regarding integration of SDOH factors into Medicaid managed care risk adjustment. They will cover risk adjustment design considerations, policy and operational considerations for actuaries and states that wish to integrate SDOH into risk adjustment, simulated variation in financial outcomes for risk-bearing organizations when such integration occurs, and variation in the relationship of SDOH factors and morbidity to modeled risk across programs and populations. At the conclusion of the session, attendees will leave equipped to think critically and act effectively with respect to SDOH in their own work, from measurement and analysis design to actuarial interventions.

Description: Toward a Predictive Analytics Framework files

Description: The rapid advancement of technology today will revolutionize how humans interact with their vehicles in the near future. Vehicle manufacturer initiatives to incorporate new technology into their products should usher in societal benefits such as improved driving safety, enhanced fuel efficiency and potentially lower costs for insurance.

Description: Artificial intelligence (AI) models have become increasingly popular in various industries, including finance. Such models can help lenders assess the risk of loan applicants, identify potential defaults and make better decisions about granting credit. However, the complexity of many machine-learning and, particularly, deep-learning models makes it difficult to understand how they arrive at their decisions. This lack of interpretability can be a significant problem in the legal and ethical realms, as it hinders transparency and accountability. Join us to learn interpretability techniques that are essential to address the challenges of using complex AI models in credit risk modeling. These techniques aim to provide a better understanding of how an AI model arrived at a particular decision or prediction. Techniques include surrogate models, which aim to provide a simpler model that approximates the behavior of the original model, and decision trees, which show the decision-making process in a more transparent way. However, applying interpretability techniques to AI models can be a challenging task. For example, some techniques can reduce the performance of the model, which can be unacceptable in applications where high accuracy is critical. Additionally, some techniques may only be effective for certain types of models or datasets, which limits their applicability. Despite these challenges, interpretability techniques are becoming increasingly important in the field of credit risk modeling. Financial regulators have recognized the importance of interpretability, and are starting to require financial institutions to use models that can be explained and validated. In addition, interpretability techniques can be used to improve the performance of credit risk models. By understanding how a model makes decisions, it is possible to identify areas where the model can be improved or where additional data may be needed.

Description: This session will discuss essential theories and practical applications of deep learning for actuaries. Participants will gain insights on leveraging these cutting-edge techniques to enhance actuarial models and drive predictive accuracy.

Description: "A crucial importance in forecasting is to be able to distinguish cases when temporary slowdowns in health care utilization are followed by a “rebound” period of higher utilization. Come explore an analysis of a new mathematical model describing the return-of-care process. By means of simulation and case studies using the R programming language, the relationship between the visibility of these effects and the endogenous variance of the utilization time series is explored. After attending this session, you will be able to: Describe the parameters and mathematical form of the model Apply the model to real-world utilization data"

Description: The expanded use of predictive models, algorithms and external consumer data has drawn the attention of the life insurance industry to the matter of fairness and bias in underwriting, including proposed regulation in states like Colorado and New York and a draft NAIC Model Bulletin. Insurers will benefit taking a proactive approach to verifying that their practices, both current and future, do not result in unfair discrimination. This session will help attendees in understanding potential requirements and reporting insurers must address, techniques and tools for evaluating bias, and challenges in doing so. At the conclusion of the session, attendees will be able to: o Understand proposed regulations and practices regarding fairness and bias o Identify tools and techniques for evaluating bias in their processes o Discuss the challenges the industry will face in addressing fairness in underwriting

Description: Much of the work performed by disability insurance actuaries depends on the availability of accurate and detailed data, which is not always as simple as it sounds. Explore a variety of data challenges faced by disability actuaries, along with potential solutions. Potential topics include finding relevant data, the impact of poor data on valuation work, the impact of new privacy rules, and the potential bias in the data used to develop predictive models.