Description: Artificial intelligence (AI) and Machine Learning (ML) are accelerating us into the fourth industrial revolution. In the next few years technological change and innovation will be rapid. The implications of AI on the actuarial profession are real and game changing. This session will help health actuaries understand what to expect from AI, how to begin using AI, and how AI will dramatically enhance the actuarial profession in the near future.

Description: Often actuarial practitioners are faced with working with data that is less than ideal. The data may be observed with gaps in it, a model may suggest variables that are observed at different frequencies, and sometimes predictive analytic results are very fragile to the inclusion or omission of just a few observations in the sample. Data, particularly big data, are often "messy" and something must be done about it. What is the actuary to do about these very practical matters? These types of questions are what this presentation is intended to address. Concerns on missing data, outliers, nonlinearity, mixed-frequency, cross-correlations are illustrated using real datasets in the Asia-Pacific countries. Some possible solutions to the messy data problems will be discussed.

Description: Feature article describing how to use advanced predictive analytics for rate making in the insurance industry.

Description: As M2M are exponentially increasing, we will soon see reinventing of whole business models and customer relationships.

Description: This abstract describes a paper that defines a predictive model for assessing risk associated with information systems.

Description: A description of the operation of an R package for experience studies. Premium patterns, lapse rates, and mortality rates can be calculated.

Description: This project obtains ensemble simulations of surface atmospheric temperature over North America.

Description: The Modeling Section, Predictive Analytics and Futurism Section, Committee on Life Insurance Research, Product Development Section and Reinsurance Section releases a report that can help to educate actuaries on how best to implement predictive modeling into relevant areas of actuarial practice. This report includes a review of existing literature and current industry practices, as well as a comprehensive set of considerations for predictive modeling in insurance applications.

Description: The aim of this project is to present proposals for Variable Uninsured Life Annuities—or “Value annuities.” The report and the accompanying models illustrate how Value annuities work.

Description: Even the best algorithms are only effective if they are trained on appropriate data. This article discusses common pitfalls in creating a training data set.