Description: Highlights from the 8th Intercompany Long-Term Care Insurance Conference held in March 2008, consisting of 56 sessions covering a range of long-term care insurance LTCI topics each with a track-specific focus.

Description: On October 30, 2015, the SOA Assumption Development and Governance Group, an informal discussion group consisting of nearly 200 interested actuaries with topics pertaining to actuarial assumption development and governance, organized an industry discussion call on end-to-end assumption documentation practices. The purpose of this call was to generate a large list of ideas for best-practice assumption documentation. More than thirty companies were represented in the call, including direct insurers, reinsurers and consulting firms. This article is the work product of the discussion written by Laurie Li and Alex Zaidlin.

Description: Deep learning neural network applied to experience analysis for post-level term lapse and mortality.

Description: This article delves into the transformative realm of Business Intelligence (BI) tools. We explore the fundamental functionality and structure of these tools, and through case studies illustrate how they offer valuable insights into carrier experience and underwriting dynamics. From real-time data visualization to in-depth data analysis, discover the essential features that empower businesses to make better informed decisions.

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.

Description: This article discusses a study of the impact of the drug infliximab on Crohn's disease patients. This study had been approved in response to an SOA request for proposals for research on the health cost and utilization effects of a specific prescription drug.

Description: Summary of industry practices on assumption governance, trend, challenges, and opportunities.

Description: Actuaries can empower their understanding of policyholder behavior with third party data. Modeling policyholder behavior should start from developing knowledge of who they are, instead of actuaries assuming what a rational behavior should be.

Description: In this article, we introduce 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.