Description: This session will cover lessons learned during the course of implementing PBR by the panelists. It will focus on areas that were difficult to interpret, unexpected issues and managing the process. It will focus on potential stumbling blocks from an implementation, pricing and product development standpoint. There will also be an overview of YRT treatment to date and an update on any emerging best practices.

Description: Regulatory change and increased focus on internal risk management are driving a renewed interest in model efficiency. In this session, we will review several new and existing tools, that show significant promise for advanced modeling of equity linked products. These include: • Clustering • Use of unique--and potentially a different number of--scenarios for each policy • Semi Monte Carlo (SMC) – this is a proprietary technique that is similar to a combination of Monte Carlo and numeric integration • Using a neural network approach to optimize some of the more complex and manual aspects of clustering and improve the fit of the clustered model • Combining SMC with the use of unique scenarios per policy

Description: Presenters will discuss mortality improvement as it applies to various lines of business with an emphasis on how individual life findings can be used to fine tune group life assumptions. In particular, it is important to know that there is not a single percentage of annual mortality improvement. Rather, experience shows that the rate of mortality improvement varies by factors such as attained age and target market.

Description: Predictive models can improve the traditional actuarial assumption-setting process. Data science techniques can provide deeper insights into experience through their ability to identify key drivers, rank importance and account for interactions. The presenters will cover ways in which companies can utilize predictive analytics to set assumptions, including the various methods available and practical approaches for implementation. They will also discuss the advantages and challenges of using predictive models for setting assumptions for life, annuity and disability products.

Description: There are two main equity release plans for retirement financing: reverse mortgage plan and home reversion plan. Both plans entitle the home owners to release cash from their properties without leaving their home. In the lease buyback scheme (LBS) recently introduced rin Singapore, the home owner sells the tail-end of the property lease to the government in exchange for a cash payment upfront. Unlike the two main equity release plans, the LBS only allows the owner to stay in the property during the front part of the lease but not for life. In this paper, we propose a hybrid home equity release plan that incorporates both features of the home reversion plan and the LBS. We provide an actuarial framework to analyse the pricing of the hybrid plan. Some numerical illustrations are presented to show the actuarial values of the plan under different parameter choices, such as lease period and portion of property values sold. The hybrid plan provides enhanced flexibility to plan takers to meet their retirement needs.

Description: Regulatory change and increased focus on internal risk management are driving a renewed interest in model efficiency. In this session, we will review several new and existing tools, that show significant promise for advanced modeling of equity linked products. These include: • Clustering • Use of unique--and potentially a different number of--scenarios for each policy • Semi Monte Carlo (SMC) – this is a proprietary technique that is similar to a combination of Monte Carlo and numeric integration • Using a neural network approach to optimize some of the more complex and manual aspects of clustering and improve the fit of the clustered model • Combining SMC with the use of unique scenarios per policy

Description: Andy Rallis delivers his speech at the presidential luncheon of the SOA 2019 SOA Annual Meeting & Exhibit in Toronto.

Description: Natural Language Process (NLP) techniques can be used to find insights in large unstructured data sets and Word Embeddings are pervasive on a wide spectrum of NLP applications. These word representations improve downstream tasks such as Sentiment Analysis, Recommender System, and Topic Modeling. Learn how NLP transforms the Insurance Industry; and how word embeddings and pre-trained models improve the effectiveness and performance of NLP applications. NLP is increasing in importance for insurance companies. Additional application examples are available in session 36.

Description: This session will look into life insurers’ anticipated business impacts as a result of the implementation of the new accounting standard for insurance contracts, IFRS 17. What will be the financial impact as of day one as a result of transition? How will embedded value for common life insurance products change? How will costs of reinsurance be affected? Will products have to be re-designed and/or re-priced? IFRS 17 may have more ramifications into the way insurers are doing business than we have anticipated so far. While we are working on the implementation of this new standard, we should not lose sight of the business impacts that will follow. At the conclusion of the session, attendees will be able to: Understand key impacts of the transition to IFRS 17; See illustrative examples of the impact on embedded value; and Understand key impacts on product design and pricing Country Relevance: US and Canada