Description: Adjusting GAAP reinsurance reserves to account for reinsurance protection against the events that trigger direct reserve constraints (such as NPR capping or LFPB flooring) can be a challenge any time. Ceding a block of business that is already in force increases the challenge—especially if one of those constraints was already present at inception of the reinsurance. This article builds on previous work (published in the July 2022 and June 2023 issues) to show how to measure initial reinsurance reserves in a way that complies with AICPA guidance and prepares for effective measurement of subsequent changes in the effects of the constraints.

Description: With coinsurance of an existing block of long-duration insurance contracts, there may be existing reinsurance that remains in force. The new coinsurance is typically net of such “inuring reinsurance.” In this article, we look at approaches that the new reinsurer might apply to account for the effects of inuring reinsurance.

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.