Description: The optional phase-in period for life principle-based reserves (PBR) has come to a close, and companies have put in the work to bring their PBR implementations across the finish line. With the mandatory PBR implementation deadline behind them, companies can turn their attention from compliance to model and process improvements. The presenters will outline lessons learned from PBR implementations and their applications to broader use cases, as well as resources that are available for PBR modelers. Discussion topics will include items such as: Model simplifications and validation Model run-time techniques Model scalability (e.g. adding new products / future assumption updates) Sensitivity testing Model projections Available PBR & other modeling resources (e.g. PBR practice note, ASOP 56)

Description: Commentary on practical observations resulting from constructing and running Economic Capital models. Possible standardization of assumptions and result interpretation are morphing even though use of E.C. models has now been around for years.

Description: Summary of the SOA research project on PBR Simplified Methods. Describes the multi-risk scenario generator, central estimate assumptions, assumption objectivity measures, and regulatory demonstrations per VM-20.

Description: Producing a crystal-clear balance roll-forward on time, obtaining a fresh model output the first time or providing model results for your business partners with a tight turnaround all depend on one thing: how fast the model engine runs. Authors explored various reasons behind significant computational power consumption, and discussed different ways to speed the computational process such as in-force population compression, model use case consolidation, code simplification and streamlining, and infrastructure automation, etc.

Description: Spark offers a way to get some dramatic speed and scalability advantages over the Map-reduce methodology whenever you are doing iterative data processing and particularly when you want interactive data analysis capability. Find out why “lazy execution” can be a desirable characteristic when dealing with big data.

Description: "Visual storytelling is frequently used to effectively convey complex actuarial concepts to our clients and other audiences. When talking about data visualization, we often focus on the explanatory aspect. But data visualization is also a crucial tool in developing insights from large and complex data sets at every stage of data analytics spectrum: • descriptive (what happened?), • diagnostic (why it happened?), • predictive (what will happen?), • and prescriptive (how do I influence what will happen?). In exploratory and modeling stages of data analytics’ project, we let the data tell the story or explore our intuition and hypothesis through data pictures. We demonstrate the power of visual display in healthcare data analytics through vivid examples from the healthcare case studies. These illustrations of data visualization exploratory power range from assessing the quality of data or examining outliers, to exploring variables’ relationships and trends, to hypothesis testing, to guiding in feature selection and models’ comparison and evaluation, to model validation. Throughout these illustrations, we will discuss principles of graphical effectiveness, excellence and integrity."

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: Commentary on practical observations resulting from constructing and running Economic Capital models. Possible standardization of assumptions and result interpretation are morphing even though use of E.C. models has now been around for years.

Description: This article walks through the history of model efficiency in the U.S. life insurance industry, examines its current application, and looks ahead to what we might expect to see in the future.

Description: This article demonstrates how to implement DevOps for data using Moody's Axis. This was described as Model as Data (MAD). It described how extract turn-around documents from the model so they could be loaded back into the model. This feature allows continuous integration, continuous deployment and continuous testing of the model, which are important concepts in DevOps. This will allow the actuaries to speed up the model development cycle.