Description: While many know that machine learning is a big deal and even have a general idea of what it is, many do not know what machine learning can do for them. As an alternative to citing achievements or explaining algorithms, this article outlines the challenges that occur in statistics and the solutions that machine learning offers. Some of those challenges include correlated predictors, missing data, data interaction, and prediction intervals. Corresponding solutions include regularization technics, missing value imputation with KNN, tree based models, and cluster analysis for backtesting.

Description: Pandemic impact on continuing education. Financial Reporting Section and Community Engagement. US GAAP textbook update for LDTI. IFRI textbook update for amendments.

Description: Accelerated underwriting expert, Ryan Holt, FSA, gives a brief history of the confusion matrix and how its use came into the accelerated underwriting space. An in depth discussion of estimating mortality impact using underwriting audits follows. Three key assumptions that effect mortality impact are discussed. Readers will leave with an understanding of how to estimate mortality impacts using audit results from any new under writing program as well as the considerations that should be taken around key assumptions. Background articles are provided for readers that are less familiar with the subject matter.

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: This presentation proposes a solution to the student actuarial paradox “I mastered the syllabus but failed the exam,” by utilizing the two-dimensional syllabus vehicle which pedagogically focuses on the two dimensions of content and problem difficulty. This presentation advocates the PMR characterization of three levels of problems difficulty: Plug-ins (easy), Monkey-wrench (intermediate), and Research-type(hard) questions. PMR was developed by examining difficulty levels in SOA exams, and problems of various software vendors. The author's students routinely score high on the SOA FM exam; it is hoped that these methods will assist other instructors in their quest for good pedagogy. Very briefly: “Plug-ins,” refer to multi-part problems, for example, calculating the price of an annuity that is first increasing and then level; “Monkey-wrench” problems specifically refer to plug-in multi-part problems where one component is a monkey-wrench, an issue the candidate has not previously encountered. It might be a non-typical modeling or it might be a non-typical algebraic simplification or it might be an unexpected integration of distinct modules in a manner that the candidate has not yet seen. “Research-type questions” refer to problems requiring some type of experimentation for example, looking at initial cases, seeing a pattern and then applying methods

Description: The summary and introduction of an SOA research paper that explores valuable insights and recommendations for insurance companies considering entering the market of commercial long-term care insurance (LTCI) in the Asia-Pacific, based on individual health status.

Description: Discount rate curve construction has been a topic of renewed interest following recent changes in financial reporting standards. Interpolation is a key component of curve construction and can be conducted via an assortment of methods. This article explores six popular interpolation techniques and assesses how they perform with regards to desirable features of such methods: continuity of forwards, stability and locality, simplicity, and market consistency.

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: The article describes the factors that should determine the asset allocation of an employer's QDIA, especially Target Date Funds, and suggests that in general QDIAs have insufficient equity in retirement asset allocations.

Description: The Risks Analytics Symposium 2022: Actuarial Perspectives on Climate Change was a hybrid half-day event where university students, as well as academics and industry professionals, had the opportunity to network and view live discussion panels in-person at UIUC or virtually through Zoom.