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.

Description: This article discusses key considerations and differences in measurement requirements between IFRS 17 and LDTI, leveraging a term insurance example to illustrate potential impacts on liabilities and, ultimately, earnings emergence.

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: This article highlights the fact that new requirements for disclosure of average liability duration and interest rates could lead to diversity in practice. It also recognizes that elements of the new disclosure requirements will enable financial statement users to perform their own crude estimates of these averages in ways that could help them to better understand the liabilities and to compare companies using consistent methods. Finally, the article describes how companies might also find value in such crude estimates.

Description: In November 2020 the Life Actuarial (A) Task Force unanimously passed APF 2020-08 which adds a third permissible method in the Valuation Manual to determine company experience mortality rates. This article describes the three methods

Description: How does mortality experience impact earnings under the new GAAP financial framework? This article discusses how to isolate key components from financial models related to decrements, as well as how to handle the changes in the financial reporting landscape including: the aggregation of insurance policies into cohorts, dynamic reserving, and the limitations imposed by caps and floors. Looking at the components of earnings, such as the present value of benefits, expenses, and premiums, and how these elements interact is critical to form a comprehensive earnings story.

Description: This article aims to delve into the rationale and calculation logic of the variable fee approach (VFA) which is applied to the insurance contracts with direct participation features under IFRS 17. In actual practice, the variable fee approach can be implemented in two methods, which are from fee income or total cash flows point of view. These two methods will achieve the same outcomes but are featured with different insights and varying degree of operational ease. Detailed roll-forward steps of contractual service margin (CSM) for these two methods are elaborated in the article, along with a numerical example by using a variable universal life product to help the readers comprehend the rationale behind the variable fee approach.

Description: This article provides an overview of activities that should be considered by an actuary when validating a predictive model. It describes several components to consider when validating a predictive model and provides an examination of various methodologies that can be implemented in the validation process.