Search Presentations
STAY TUNED! If you are anticipating additional search filters by attribute and level to align with the CAS Capability Model, it is coming later this Summer. As the CAS begins to code recorded sessions by specific attributes and levels (starting with the 2023 Annual Meeting), these will be tagged in the CAS database of presentations going forward and should be searchable.
But you may use the Capability Model now to help you identify topics. For example, if you want to move up one level under the content area “Functional Expertise,” you may search topics in the particular functional area to expand your knowledge.
Recorded content is searchable by Capability Model attribute and level in the CAS Online Library.
Refine Your Search
The presentation materials are offered in connection with CAS professional education offerings. © 2022 Casualty Actuarial Society. All Rights Reserved. The presentation materials may contain copyrighted content the use of which has not been specifically authorized by the copyright owner. You are permitted to view and print the materials for personal/professional noncommercial research purposes. Except for the foregoing, you agree not to reproduce, distribute, modify, create derivative works, or commercially exploit the presentation materials without prior written permission from CAS. Please direct any copyright permission inquiries regarding use of the presentation materials to acs@casact.org.
STAY TUNED! If you are anticipating additional search filters by attribute and level to align with the CAS Capability Model, it is coming later this Summer. As the CAS begins to code recorded sessions by specific attributes and levels (starting with the 2023 Annual Meeting), these will be tagged in the CAS database of presentations going forward and should be searchable.
But you may use the Capability Model now to help you identify topics. For example, if you want to move up one level under the content area “Functional Expertise,” you may search topics in the particular functional area to expand your knowledge.
Recorded content is searchable by Capability Model attribute and level in the CAS Online Library.
The Actuarial Standards Board is proposing changes to ASOP 12 on Risk Classification.
Insurance rates in many states shall not be “excessive, inadequate, or unfairly discriminatory.” The actuarial profession has long considered that rates meet those rating laws if the rates are actuarially sound. But understanding the precise meanings of “actuarially sound” and “unfairly discriminatory” requires a more nuance understanding. Today's changing views which reflect the nature of social structures and advances in predictive analytics has caused reconsideration of whether existing notions of unfair discrimination and actuarial soundness might perpetuate socially undesirable inequities in insurance products, services, prices (rates), and availability.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Ron Kozlowski
Panelists:
Bob Miccolis; Brian Mullen; Dave Sandberg
Keywords:
Professionalism
CS-6: Are MGAs the Future of Underwriting?
This session will provide two actuarial perspectives on what MGAs are, how they work, and what the MGA space looks like in the United States. It will explore some situations where a carrier may consider delegating authority and the types of risk typically involved. Case studies of product innovation in alternative markets, oriented towards addressing the needs of the underserved, will be covered. Operational considerations related to MGAs, including compliance and technology, will also be discussed. The session will be useful to anyone interested in tapping into alternative markets, or simply learning how approaches used in alternative markets can apply in traditional ones.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Jim Weiss
Panelists:
Denise Olson; Anju Arora
Keywords:
Ratemaking
CS-5: Applications of Gaussian Process Regression Models
Gaussian Processes (GP) are stochastic processes, collections of indexed random variables based on the normal distribution. In the context of statistics these processes are well known and well-behaved objects that have been extensively explored.
On the other hand, Gaussian Process Regression (GPR), is a relatively lesser-known procedure based on GP, which can be implemented both for regression and classification problems.
GPR can be defined as a supervised non-parametric technique stemming from the Bayesian field.
This is a relatively novel technique in the field of Machine Learning, only used in some niche applications. Moreover, its use is nearly unknown in Actuarial Science, with only one analysis published in the literature.
The presentation will:
a) Briefly review the theoretical foundations behind GPR.
b) Show how to apply suitable reserving algorithms based on GPR on typical insurance data sets.
c) Compare different approaches in terms of predictive performance and practical usability.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Frank Gribbon
Panelists:
Marco De Virgilis; Giulio Carnevale
Keywords:
Research
CS-4: Application of Bayesian MCMC to Reserving Noisy Data
This session will present a couple of short case studies illustrating how to estimate reserves by applying Bayesian MCMC concepts on noisy data. The first case study will apply to low frequency / high severity lines of business such as Directors and Officers or Umbrella, where the loss triangle shows zero payments in early development months and the claim severity has a heavy tail. The next case will apply to incorporating changes to reserving models, such as organizational, business, or inflationary changes.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Carl Ashenbrenner
Panelists:
Michael Larsen
Keywords:
Reserving
CS-33: Winning the Communication Battle
Actuarial work is complicated and difficult to understand and so it is hard for non-actuaries to understand our work. The problem is often exacerbated by actuaries having spent 10,000 or more hours studying technical matters but probably less than 1,000 hours developing communication skills. As actuaries advance in their careers, effective communication becomes more important than analytical work (which can be delegated to capable staff). Also, as actuaries we likely have even less experience in dealing with confrontation which can be critical when communicating bad news.
This session will provide a number of suggestions to help you and your staff become better communicators. We will also cover through two vignettes some of the more difficult communication situations that actuaries face (Presenting to Boards and Delivering Bad News).
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Kevin Donnelly
Panelists:
Brian Brown; Kathleen Odomirok
Keywords:
Business Skills
CS-32: What Everyone Needs to Know About Bitcoin & Crypto
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Martin Ellingsworth
Panelists:
Ravi Sharma
Keywords:
Emerging Issues
CS-31: Understanding the Impacts of Climate Change on Atmospheric Perils
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Carl Ashenbrenner
Panelists:
Dan Ward; Michael Tine
Keywords:
Climate Change
CS-30: Used is the New New: A Changing Auto Market
Over the last 24 months, the new car market has encountered several major disruptions. It began the pandemic shutdowns depressed the demand side of the market equation, then was exacerbated as drivers transitioned to long-term work-from-home arrangements. Then, as the market began to pick up, plant shutdowns, parts shortages, and supply chain disruptions depressed the supply side of the market equation. The used car market has shifted to fill the gaps in the new car market.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Gary Wang
Panelists:
Donald Hendriks; Matthew Moore
Keywords:
Personal Lines
CS-3: ADAS: Why Isn't It Working? Or Is It???
Using evidence from the CARFAX Vehicle Insights Program, we will investigate how Advanced Driver Assistance Systems (ADAS) are impacting auto insurers. We will review which features are the effective at reducing claims frequency, and drill into the reasons behind the apparent increase in severity for ADAS-equipped vehicles.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Bryan Brown
Panelists:
Donald Hendriks; Matthew Moore; Dushyant Pattni
Keywords:
Personal Lines
CS-29: The Tech Spectrum
The line between Insurtech and Traditional insurers has blurred over the years. Every company sits somewhere on the technology spectrum, and it is important to know how companies got to their position as well as which direction they are going. This session will cover the tradeoffs for investments in technology and innovation and the corresponding results, both short-term and long-term, expected from making those investments.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Ryan McMahon
Panelists:
Ryan McMahon; Adrian Jones; Bill O'Keefe
Keywords:
Business Analytics/Problem Solving
CS-28: Tapping Into the Next Generation of Actuaries
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Erin Olson
Panelists:
Gao Niu; Kristopher Presler; Douglas Bujakowski; Pallav Baruah
Keywords:
CAS
CS-27: Take the Pledge--Be an Actuary of the Future!
In her address to new members at the 2021 CAS Annual Meeting, Jessica Leong challenged members to be Actuaries of the Future--to apply our analytical skills to solve business problems with a tangible result. What are some examples of this in practice? How can you meet this challenge? In this session, a panel of Actuarial leaders responsible for hiring and developing actuaries will share tangible examples, ways to start putting this into practice, and answer questions. Please join us, and take the pledge to be an Actuary of the Future!
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Wesley Griffiths
Panelists:
Wesley Griffiths; Julia Stenberg; Alejandra Nolibos; Eric Kendig; Jessica Leong
Keywords:
Talent
CS-26: Spreadsheets vs R or Python?
Is the actuarial profession changing from using spreadsheets to using programming languages like R or Python? ?Hear some of you?colleagues explain why they have switched! Spreadsheets keep the data in front of the user with the?calculations hidden in the background. ?Traditional coding using R or Python keep the calculations in front of the user, with the data hidden in the background. ?See some real examples on how typical actuarial tasks are being transformed into R and Python.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Liam McGrath
Panelists:
Liam McGrath; Kevin Dalton; Patrick Yu
Keywords:
Special Topics
CS-25: Penalized Regression - Between Credibility and GBM
"Penalized regression is steadily becoming a mainstream application in ratemaking. There is a momentum in the insurance space with innovation in research, software and production on penalized techniques that build and innovate the standard GLM models.
Historically, this technique was popularized by the machine learning literature, and how it is taught is not synchronized with how actuaries approach modeling to solve insurance problems. This should not be the case: the penalized framework is versatile and allows to effectively solve many insurance use cases that are currently tackled via established techniques.
First, we will see how, practically and theoretically, Penalized Regressions are effectively Credibility procedures and allow to blend GLM with credibility to reduce overfitting and improve a model’s ability to generalize.
Then on the other hand, we will display how Penalized regression can be thought of as GBMs, a powerful but yet completely black box modeling technique.
Since Penalized regressions can effectively tie standard Credibility practices and incorporate some of the benefits of GBMs, this presentation aims to contribute the diffusion of these techniques as solid alternatives to standard GLMs for ratemaking."
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Jonathan Charak
Panelists:
Guillaume Beraud-Sudreau; Mattia Casotto
Keywords:
Predictive Modeling/Analytics
CS-24: Open-Source Actuarial Science with Examples
Actuarial science has been built on the idea of open-science with a rich repository of papers, monographs, and studies made freely available by the CAS. The CAS also has its own GitHub organization, and has allowed the open-science philosophy to be extended to open-source tooling. In this session, we will explore the benefits of open-source tools, and how we can all get involved. We will also dive deeper into the Chainladder-Python library to give a practical example of how these tools and the community that surround them can benefit you and your organization. A live demo will be run in Google Colab. If you want to follow along, all you need is a laptop with a web browser - no prior installation required. Please sign up for the associated round table if you are interested in a hands-on tutorial working session led by the speakers.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Aaron Hillebrandt
Panelists:
Kenneth Hsu; John Bogaardt
Keywords:
Predictive Modeling/Analytics
CS-23: Mitigation that Matters: A Wildfire Case Study
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Joshua Merck
Panelists:
Margaret Brinkmann; Thomas Larsen
Keywords:
Research
CS-22: Introduction to Layered GBM
In this session, the speakers will introduce an innovation on the traditional Gradient Boosting Machine (GBM), which we call Layered GBM. The GBM algorithm has established itself as a strong tool for modelers, but suffers from the reputation as being a complex, black box approach to modeling. We will describe the concept behind the Layered GBM and illustrate how this alternative provides improved interpretability of the model results, without loss of predictiveness, compared to the traditional GBM outputs. We made these adaptions in recognition we are looking at the insurance problem as a whole, and the model outputs need to provide more than a validation of accuracy. This enhanced interpretability can make GBMs more attractive to internal stakeholders and regulators.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Nicole E. McArdle
Panelists:
Justin Milam; Liam McGrath
Keywords:
Predictive Modeling/Analytics
CS-21: Inflation - An Update
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Ben Carrier
Panelists:
John Jacobi; Brian Brown
Keywords:
Inflation
CS-20: How Inflation and Enhanced Safety Features are Changing the Personal Auto Insurance Market
The annual inflation rate was at 9.1% through June of 2022, including rates of 59.9% for gasoline, 11.4% for new vehicles, and 1.7% for used cars and trucks. At the same time, vehicles are increasingly included with enhanced safety features that impact the insurance industry in a variety of ways. In this session, we will discuss the changes in the new and used vehicle market since 2020, the evolution of enhanced safety features, how these are impacting personal auto loss costs, and how companies are reacting.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Katey Walker
Panelists:
Matthew Moore; Justin Milam; Marty Ellingsworth; Katey Walker
Keywords:
Inflation
CS-2: The Actuarial Meaning of Insurance
The actuarial profession is grounded in the concepts of insurance. Many academic and other authors have written about the concepts and definitions of insurance. Actuaries have developed actuarial standards of practice, practice notes, principles, etc. However, the actuarial profession seldom explains the actuarial meaning of insurance.
Insurance laws and regulations define insurance to protect the policyholders and the public. Accounting standards define insurance to fairly represent financial statements. But actuaries tend to rely on other professions to define insurance. Nonetheless, the actuarial profession has excellent insights about the wide scope of insurance applications since actuaries provide the quantifications necessary for insurance to survive despite many unknowns and uncertainties which resist measurement.
Insurance pricing disputes arise around the definition of insurance, insurability, insurance accounting, insurer regulation, insurance taxation, arm's length pricing of insurance transactions, actuarial pricing judgments, and actuarial risk assessment of insurer solvency. The law of large numbers is oft quoted as the foundation of actuarial science for insurance. However, this statistical law does not define insurance nor the actuarial profession.
The presenters will discuss the actuarial meaning of insurance and highlight the major debates about the actuarial perspectives about the actuarial estimates necessary for insurance transactions to occur. The presenters will present examples to illustrate the potential for conflicting views and confusion when the definition and meaning of insurance is being questioned.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Jonathan Charak
Panelists:
Bob Miccolis; Robert Walling
Keywords:
Special Topics
CS-19: Hot Topics for International Actuaries
Have you ever wondered what the CAS is doing internationally? Are you interested in the issues being faced by actuaries outside of North America? Come to this session to hear from the CAS VP International on what the CAS is doing to meet the Pillar 3 objective of growing internationally. Also hear from actuaries with experience from outside of North America about the hot topics for international actuaries, whether it is IFRS17, Solvency II, climate change, or ???
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Ron Kozlowski
Panelists:
Kendra Felisky; Yvonne Palm; Ronald Kozlowski; Nicolas Vega
Keywords:
International
CS-18: The Future of Enterprise Risk Management : Six Future Scenarios
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Raj Bohra
Panelists:
Robert Wolf
Keywords:
Enterprise Risk Management
CS-17: From Theory to Practice: Applications and Illustrations of Bias Identification and Mitigation Techniques
The utilization of models and the potential for the presence of bias or disproportionate impact on certain protected classes is a pressing topic in the insurance industry today. Many have weighed in on the topic, from regulatory and advocacy groups to actuaries and data scientists, and the discussion has ranged from holistic to technical. This presentation will bridge the gap by providing practical considerations and illustrations of different approaches to identify and address potential bias. The session will begin by exploring one technique known as Bayesian Improved Surname Geocoding, that has been used across many industries to infer protected class information, specifically race/ethnicity, for the purposes of bias identification and mitigation efforts. The session will then proceed to offer easy to understand mathematical representations of some of the common approaches to identify and mitigate potential bias in actuarial data and models.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Mallika Bender
Panelists:
Mallika Bender; Michael Chen; Marc Elliott
Keywords:
Bias
CS-16: Flood Insurance: An Update
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Joseph Becker
Panelists:
Andy Neal; Derek Lynch; Joseph Becker
Keywords:
Catastrophe/Reinsurance
This session will be represented as a case study and role playing where the Enterprise Risk Professionals will be communicating his/her quarterly ERM and/or annual ORSA report to the Board. What style of presentation is recommended to gain optimum buy-in, understanding, and support from your Board?
Risk Appetite statements are often vague and qualitative, making it challenging to make the connection to day-to-day decision making. In this session, we discuss leading practices for defining risk appetite clearly and quantitatively, providing a direct and actionable line-of-sight to decision making.
Join us in an interactive session where panelists will be involved in role-playing in the interest of generating interactive discussions with the audience.
Source:
2022 Annual Meeting
Type:
Concurrent Session
Moderators:
Bob Wolf
Panelists:
Robert Wolf; Michelle Baurkot; Daniil Shalmiyev; Raju Bohra
Keywords:
Enterprise Risk Management
