Description: PartnerRe Life and Health is rapidly growing its presence in global markets. This growth means that our medical underwriting team has to handle 25 percent more cases every year. To manage these additional cases without increasing headcount at the same pace, the team has to operate more and more efficiently. In a market where response time is a key differentiator, we improve efficiency by using machine learning to triage and prioritize the underwriting team's case work. In this talk, we describe the model pipeline end to end. That is, we cover the entire implementation chain from accessing data to the eventual evaluation of the added value. In particular, we discuss often neglected topics such as model risk mitigation, technical deployment of the model and integration into business processes.

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: Big data and predictive models have disrupted the life insurance new business and underwriting processes over the past few years. How did we get here? What does the future hold? This session will review the lessons learned from the evolutionary process and discuss what the potential next steps are in this journey. Are real time fully underwritten decisions an achievable goal?

Description: Learn the fundamentals, promises and myths of blockchain technology; why it's important and relevant today, and how it's evolving our relationships with data, analytics and the science of product development and maintenance. Discuss examples and details with Susan Joseph, and Truman Esmond, VP Solutions and Partnerships for AAIS and Technical Lead for openIDL, AAIS's blockchain network for regulatory reporting.

Description: As technology changes the insurance landscape, it is essential that companies adapt quickly while staying focused on customer needs. This presentation will show how Agile and Design Thinking methodologies can help business and technology teams quickly test new ideas and optimize value delivery.

Description: In the insurance industry, machine learning models are increasingly used to make decisions that affect people's lives. In order to ensure that models are fair, they should be audited for bias. There are no hard and fast rules for bias audit; metrics that can be used to evaluate fairness vary depending on the context in which the model is deployed. In this session, we present a flexible framework that highlights key considerations in bias evaluation that can be adjusted to suit your process. In this session, we will learn about different metrics to assess fairness, discuss open source tools that can be used for bias audit, and walk through a case study.

Description: If you’re looking for a quick and easy way to begin exploring data analytics, machine learning, and AI, Microsoft has created a number of Data Science Virtual Machine images which include many of the most popular ML/AI tools pre-installed. In this presentation, we will start from scratch and demonstrate how to get onto the Azure cloud, fire up and connect to a Data Science VM, upload data, and train a machine learning model. While this presentation will use Microsoft’s Azure cloud, many of the concepts should be directly applicable to AWS or GCP.

Description: This year's session will focus on the recruiting side - trends in what companies look for, trends in candidate interests, and methods for finding the right candidate

Description: Recent Population Cause of Death Trends and Implications for Life Insurance

Description: The discount rate is one of the most critical topics in IFRS 17, which may have important repercussion on product profitability. Having a low discount rate may indicate a low profitability of a group of contracts, while a realistic expectation may differ. A similar issue was prevalent especially for U.S. companies when discount rates were set using a market consistent framework. The session is intended to help develop a discount rate framework that aligns with the business practices and address the concerns around the market consistent framework. This session will cover practical implementation considerations to set and apply IFRS 17 discount rates. The panelists will discuss alternative approaches to allow for a level of illiquidity premium for business supported by fixed assets with credit risks. Discussions will also cover other implementation considerations including granularity of setting the discount rate, application to new business, implications on asset and liability modeling, and a planning aspect for a successful implementation of the discount rate setting process. The panelists will share case studies to illustrate different approaches of setting the discount rate and their potential financial impacts. At the conclusion of the session, attendees will be able to: understand key requirements of setting discount rates under IFRS 17; understand how to align the discount rate to the actual business practices; understand implications of the discount rate in actuarial modeling; understand potential impacts on financial results; and develop a realistic plan to set discount rates appropriate to the business practices.