Description: This paper addresses some pervasive problems in using secondary data in actuarial research. An approach to solving these problems is based on information theory. From Transactions of Society of Actuaries 1995, Vol. 47.

Description: Using data from a large insurance company, we construct a parametric model for the joint survival function based on a Hougaard copula function.

Description: A mathematical framework for benefits and choices must be created, in order to model flexible benefit selection. This paper creates such a framework by defining benefit plans as reimbursement functions. These are then used with a defined choice function to calculate the cost deviation due to selection. From Actuarial Research Clearing House 1992, VOL. 1.

Description: At this session, experts will provide an overview of current statutory valuation issues pertaining to life and annuity products. The focus is on activities of the American Academy of Actuaries relative to principle-based approaches, but other matters will be covered, including the status of the NAIC valuation manual, life risk-based capital, developments at the NAIC affecting life insurance companies, and practice issues for appointed actuaries.

Description: The author previously wrote about extending the general nonparallel shlft approach to duration analysis. This paper explores the immunization properties of that model. In addition, applications to asset-liability management are explored. From Actuarial Research Clearing House 1990 VOL. 2.

Description: 1996 Valuation Actuary Symposium. In this teaching session on liability modeling, the panelists discussed the key aspects of identifying and gathering the data required to construct models, the model building process including objectives and considerations, and the modeling process from the standpoint of policyholder and company behaviors.

Description: The Delphi Method is discussed in detail. The method attempts to filter out the consensus bias that can result from societal forces by employing a technique whereby an anonymous collection of opinions is used, supplemented by feedback loops that can be used to influence outcomes.

Description: This paper suggests a new model for the distribution of deaths between two adjacent integral ages which addresses existing discontinuities. Application of the model is shown and compared with the existing three popular models. From Actuarial Research Clearing House 1994, Vol. 2.

Description: In this session 35TS of the 2004 Valuation Actuary Symposium, the instructor provides simple tools and guidelines to better ensure that correct conclusions are drawn. This material is presented without the use of complex mathematical formulas. Topics include appropriateness of the assumption of normality including discussion of the distribution of a conditional tail expectation, drawing inferences about population means and tail percentiles, and uses and pitfalls of linear regression analysis.

Description: Ever wanted to do a Kaggle data science competition, but didn't know where to start? This presentation meets the needs of actuaries interested in predictive analytics and competitive data science. The presentation will describe the nature of competitive data science, and provide insights into lessons learned by competing in the Airbus Ship Detection Challenge at Kaggle, as well as other Kaggle competitions. The presenters will provide an introduction to neural networks and describe the nature of the Airbus Ship Detection Challenge and other Kaggle competitions, plus a solution approaches that can be used to obtain top scores using Convolutional Neural networks (CNNs), random forests and boosted trees.