Description: What is a "super" model? How do we develop, maintain, and visualize them? What is the difference between models and assumptions? Most importantly, how can we use all of this to quantifiably improve risk management?

Description: The presenters will explore policyholder experience data for long-term products, risks of over-fitting data in developing behavioral models, and ways to mitigate these risks and develop a sustainable and coherent framework to translate complex policyholder behavior experience data to behavioral models using company- and industry-level data. At the conclusion of the session, attendees will be able to: - Identify key drivers of policyholder behavior for long-term product - Understand the risks of over-fitting data and a false sense of precision in developing behavioral mode - Understand techniques that can be used to mitigate these risk

Description: As more term insurance policies move to the post-level period, actuaries are evaluating policyholder behavior and expected mortality. Enough experience has now emerged to provide a spectrum of outcomes that can model the relationship between premium increases, persistency and mortality. The presenters will share findings and consider how different post-level premium structures produce different results.

Description: This article discusses considerations for statistical biases that may arise in LTC blocks due to historical benefit reductions. The article explores these biases in the context of experience studies and experience projections.

Description: While our ability to access and analyze large quantities of data is better than ever, many long-term products suffer from sparse data in critical risk areas, such as deep in-the-money lapse experience and long-term utilization rates for income guarantees. The presenters will explore industry-level annuity experience data for these types of situations, and discuss quantitative approaches to addressing them in pricing and other applications.

Description: Milliman was engaged by the SOA to conduct two Accelerated Underwriting (AU) surveys, one of direct companies and another of reinsurers. The surveys explored actual results from 2019–2021 and expected results from 2022.

Description: In recent years, vast amount of data from emerging experiences has helped insurers gain a deeper understanding of their policyholders and the factors driving their behaviors. However, due to limitations in traditional experience study methods, this understanding typically remains at the cohort level. This series of articles proposes a novel machine learning-based model that analyzes and predicts policyholder behaviors at the individual policy level. Policyholder embedding representations are learned using a Recurrent Neural Network (RNN) that takes into account the sequence of historical transactions associated with a policy. Additionally, a Neural Network with a multi-head architecture is trained to predict the policyholder's next action based on the policyholder embedding and other policy attributes. The resulting model offers several advantages over traditional experience studies and assumption-setting methods, including the ability to set policy-level assumptions that improve reserve accuracy, predict multiple behaviors simultaneously while capturing the interrelationships between them, and generate policyholder embedding representations that are useful for segmentation.