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.
Predictive Modeling Pitfalls - When to Be Cautious
There are many success stories featuring Predictive Models, but what does not get so widely reported are the failures: mistakes that range from subtle misinterpretations and minor miscues to unvarnished disasters. Under what conditions should a Predictive Model be the tool of choice and when should it be used with care? This session will feature several short hypothetical vignettes illustrating common pitfalls and participants are invited to share their own experiences whether they are horror stories or tales of triumph.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
The Emerging Technologies of UBI
This roundtable will discuss the many challenges around UBI technology: selecting vendors, data sources and devices, keeping pace with technological change, the consumer experience, the installation period, and cost/benefit tradeoff.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
The Agent's UBI Experience
Insurance companies selling their UBI product through agents must consider not only the consumer experience, but also the agent experience, to realize successful sales campaigns. This roundtable session will focus on UBI from the agent's point of view, with topics including agent training, incentives, and support.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
What Software Do You Use to Build Your Model?
In this roundtable we will discuss the advantages and disadvantages of different analytical software choices including R, SAS, Visual Basic, and any others suggested by the group. We will also discuss strategies for incorporating new software in a business culture heavily reliant on another kind of software.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Looking for Profit in Homeowners Insurance
The moderator will lead an open discussion on the latest trends in the homeowners insurance environment and their impact on a company’s goal to develop and maintain a profitable book of business.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Homeowners Telematics
Auto telematics has become common in the Automobile insurance market, offering new insights into how an insured interacts with his or her car, and what it means for pricing. Will technology help insurers develop a similar understanding for an insured and his or her home? How quickly will it happen?
Some major differences will come into play. First, significantly more can be measured in a home. Second, homeowners stand to benefit greatly from the availability of less intrusive hardware poised to create and transmit great quantities of data. This session will discuss the challenges Homeowners insurers may face in adopting telematics-based approaches to pricing. Questions such as the following will be addressed: What are the regulatory and privacy concerns? What can be collected now, and what is in the works? How much does the equipment cost, how easily is it installed, and how will consumers be incented to do so? And how much data is too much?
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
Stephen Lekas
Using Predictive Modeling Beyond Ratemaking
We will explore ways insurance companies use predictive modeling beyond ratemaking. Some examples include product management, underwriting, and agency/sales management. If you are using predictive modeling in interesting ways beyond rate making, and would like to talk about it, or explore how to do it, please come join us for this engaging discussion.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Predictive Modeling: Part I — (Morning Session)
A Laptop is required for this workshop.
This popular, hands-on, interactive predictive modeling workshop has been offered at the RPM seminar now for several years. It will be conducted exclusively in the R statistical computing language, which is widely adopted by statisticians and data scientists.
The course will provide a refresher of regression theory before proceeding to a variety of practical modeling applications and case studies. The focus will be on General Sessionized linear models (GLMs) – their specification, interpretation, and validation. A variety of distributions will be covered, including classical, Poisson, logistic, gamma, and Tweedie. Other topics will be discussed and illustrated as time permits. All datasets will be distributed to attendees prior to the seminar.
Important note: familiarity with R is assumed. An "introduction to R" presentation will be distributed before the seminar which will contain a primer on basic features and statistical functions, as well as installation instructions, that will enable beginners to get up to speed. While R beginners are encouraged to attend, they should make some attempt to become comfortable with the language prior to the workshop. This workshop has been designed for beginning predictive modelers, but more experienced modelers seeking a refresher or a deeper working knowledge of R have attended past workshops and expressed satisfaction with the coverage of topics.
Detail on the morning session:
The workshop begins with a refresher of ordinary least squares regression, and then provides motivation for the General Sessionization to GLMs. Students will practice specifying model forms, including link functions, distributions, weights and offsets. Additional topics include grouped data and nonlinear transformations. Small "textbook" case studies illustrate the concepts and build familiarity with R.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
John Baldan, Mark Goldburd
Lights!  Camera!  Professionalism!
Come enjoy the acting of some fine fellow actuaries who will take on several skits involving professional dilemmas. The skits have been refreshed, but as always they will lead to some lively and educational audience discussions. You will walk away from this session with a better understanding of the ASOPs, codes of conduct, and how to apply them when you face your own professional ethical dilemmas. This session may provide attendees with Professionalism Continuing Education credits.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Panelists:
Michael Chen, Kathryn Walker, Emilee Kuhn, Adina Landesman
Competitive Analysis
Quality competitive analysis is important for companies in understanding the performance of a rating plan. This roundtable session will focus on identifying and overcoming the many challenges of competitive analysis, including data, competitor selection, comparative raters, tier, coverage alignment and competitive positioning.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Building a Data-Driven Culture
Let’s face it, when a data analytics initiative fails it is usually because of shortcomings during the implementation phase. Success is dependent on getting our teams bought in and trained on how to incorporate analytics into their daily workflow. This roundtable discussion will focus on how to optimize the change management and user adoption process before, during and after a predictive analytics implementation.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Health Care Reform — A Roundtable Discussion
Join an open discussion on the impact healthcare reform has had on risks for all stakeholders - employers, providers, insurers, and patients.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Ratemaking ASOP
What is the difference between Ratemaking and Pricing Actuaries? Are the revised Ratemaking Principles and the new Ratemaking ASOP a dramatic departure from the 1988 Ratemaking Principles or simply a clarification? These are some the questions we will discuss, at what should be a lively discussion involving regulatory, consulting and insurance company actuaries, including past and present authors. The debate goes to the core or the actuarial role in the insurance process.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Penalized Regression
General Sessionized Linear Models (GLMs) have been widely used for decades. GLMs are very popular because they can model a wide range of phenomena as well as the availability of software to fit such models. GLMs typically suffer from overfitting and the inability to deal with highly correlated variables. Another common challenge for the modelers is to choose relevant variables to include in the model when faced with thousands of variables to choose from. Penalized regression is a set of regression techniques that impose constraint/penalty on the regression coefficients. They are General Sessionization of GLMs and include techniques such as Ridge regression, LASSO and Elastic Net. They don't suffer the same problems as GLMs and they can be used as a powerful variable selection tool as well. In this presentation we will give an overview of these techniques and their use in actuarial science.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
Mohamad Hindawi
Use of Analytics in Claim Management
Claims represent the biggest cost within a property and casualty insurance company. Managing the claims process is fundamental to the company’s profitability; moreover, an effective claims operation drives customer satisfaction and policyholder retention. Given the importance of the claims management function and the vast amount of information collected on each claim, it is no surprise that analytics can provide substantial return on investment for insurers. This roundtable will discuss the opportunities, challenges, and critical issues to consider when using analytics in claims management.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Predictive Modeling: Part II — (Afternoon Session)
A Laptop is required for this workshop.
This popular, hands-on, interactive predictive modeling workshop has been offered at the RPM seminar now for several years. It will be conducted exclusively in the R statistical computing language, which is widely adopted by statisticians and data scientists.
The course will provide a refresher of regression theory before proceeding to a variety of practical modeling applications and case studies. The focus will be on General Sessionized linear models (GLMs) – their specification, interpretation, and validation. A variety of distributions will be covered, including classical, Poisson, logistic, gamma, and Tweedie. Other topics will be discussed and illustrated as time permits. All datasets will be distributed to attendees prior to the seminar.
Important note: familiarity with R is assumed. An "introduction to R" presentation will be distributed before the seminar which will contain a primer on basic features and statistical functions, as well as installation instructions, that will enable beginners to get up to speed. While R beginners are encouraged to attend, they should make some attempt to become comfortable with the language prior to the workshop. This workshop has been designed for beginning predictive modelers, but more experienced modelers seeking a refresher or a deeper working knowledge of R have attended past workshops and expressed satisfaction with the coverage of topics.
Afternoon session details:
In the afternoon session, we will focus on the mechanics and methodology of modeling. Variable selection and model validation concepts will be illustrated using case studies. Also covered: graphical analysis of model fit, model diagnostics such as residual analysis, analysis of deviance, and F-tests. Model validation topics will include lift curve analysis, bootstrapping, and cross-validation.
Finally, a more in-depth case study will illustrate how to convert a business problem into an appropriate model design; data preparation; the "level" of analysis; target variable specification; GLM-based modeling of frequency, severity, and pure premium; missing values; exploratory data analysis; variable selection and transformation; multicollinearity; interpretation of model parameters and diagnostic output; nested model comparison; and evaluation of model segmentation power. Other topics will be discussed as time permits.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
John Baldan, Mark Goldburd
Value-Based Pricing
What Do People Buy? It is a deceptively simple question: What are we getting paid for? Still, many businesses arrogantly assume they know what their customers want, and believe that is exactly what they have been giving them for years. This is a myopic vision, and potentially harmful. This roundtable will be a thought-provoking discussion, focusing on buying behaviors of consumers and businesses and their impact on the insurance industry.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Predicting Homeowners' Losses: Which Characteristics Matter?
This roundtable session is focused on the many challenges to writing profitable homeowners business, with discussion topics including by-peril rating, emerging variables and data sources, use of catastrophe models, and other hot industry topics.
Source:
2015 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Actuaries are from Mars, Underwriters are from Venus: How We Work Together in Predictive Analytics
Predictive Modeling (PM) is often proclaimed as a new magic bullet for growth and cost management; and it can be that. While at its base PM is a complex process, actionable output is the goal. The panel, consisting of an actuary, an underwriter and a predictive modeler will discuss their experiences in defining actionable output, screening signal from noise, and in the surmountable difficulties in moving an organization down the continuum towards more data-driven decisions.
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
Jonathan Hayes, Christopher Cooksey, Kimberly Holmes, Richard Clarke
Insuring for Sustainability - Underwriting for Sustainable Development
Sustainability focuses on the core business of insurers. Insurers provide a unique case in sustainability since they not only manage their own risks from business activities but the core functions concern with managing risks of customers while remaining profitable. The industry bears the financial consequences from internal inefficiency, unsustainable behavior and business practice of clients and partners along the insurance value chain. Thus, sustainability affects the insurers' financial statements which directly ties to Environmental Social Governance (ESG) performance of the company and its clients, thus making ESG assessment vital to the success of the firm.
Accenture, Deloitte, Harvard Business School, McKinsey & Company and others have released global surveys, reports and data-driven case studies to prove sustainability megatrend and imperative. Enlightened businesses are focusing on sustainability practice in terms of products offering, branding, corporate governance, human capital management, social responsibility and community involvement. In the insurance arena, several leading (re)insurers have been incorporating Principles of Responsible Investment (PRI) and Principles of Sustainable Insurance (PSI) in their asset and liability management.
As global trends –environmental, social, political, technological –continue to shift the foundations of our current business models, sustainability is becoming embedded in corporate behavior, metrics and strategy. It will become increasingly important for successful business managers, especially underwriters, brokers as well as risk professionals, to develop systems thinking and sustainability knowledge to inspire global shift towards a sustainable future.
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Moderators:
Rebecca Williams
Panelists:
Jim Jones, Fan Yang, Rodney Taylor
Underwriting & Actuarial Interaction: Decision-Making in the Underwriting Process
The traditional function of the actuary in the underwriting process is ratemaking: setting base rates & rating plans, and individual account rating. In this session, we will explore some additional aspects of underwriting where the actuary is usually not included, but where he/she has important expertise and perspectives. Additionally, we will get an underwriting perspective about the importance of non-numerical information and the range of stakeholders who must be considered in order to move beyond a spreadsheet answer to a workable solution. The actuary’s participation in these non-traditional functions increases his/her contribution to the company and, at the same time, builds value for the firm as well as professional value for the individual.
We will discuss the following topics:
• Determining what actuaries do well versus what underwriters do well and how their skills can complement each other.
• Assessing the different ways pricing actuaries and underwriters interact when making pricing decisions.
• Identifying the range of stakeholders to be included in pricing discussions.
• Compromising without being compromised.
• Considering legislative, underwriting, and claims handling changes: theoretical verses market treatments.
• Understanding the role and value of the actuary at underwriting audits.
• Recognizing the value of bringing an actuary to meet the brokers and clients.
• Learning how to move into nontraditional roles.
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Moderators:
William VonSeggern
Panelists:
Klayton Southwood, Alietia Caughron, Douglas Benedict, David Perez, Chuck DiGrande
Leading Practices in Automating Underwriting for Small Commercial Insurance
In this session, the panelists will discuss how leading insurance companies use automated underwriting, powered by analytics, to accelerate profitable growth in the small commercial insurance marketplace. In fact, industry research indicates that certain small business customers may have an appetite for purchasing commercial insurance direct from carriers. In response to this emerging trend and financial pressures, automated underwriting initiatives that focus on improving no-touch / low-touch flow rates in existing portfolios, may be part of a disruptive marketplace strategy, or fall somewhere in between. In these scenarios, achieving business objectives requires consideration of the impacts to product design, pricing, and organizational capabilities.
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Moderators:
William VonSeggern
Panelists:
Matthew Carrier, Kelly Cusick, David Ovenden, Vinu Kuriakose
The Modern Underwriter: Wearing More Hats and Carrying a Bigger Toolbox
"Underwriting" is no longer a consistent role across the insurance industry. Talk to a an "old school" underwriter and you will likely hear about a sea of desks, the occasional mainframe computer, and green screen applications for the most sophisticated of companies back in the day. Today, underwriters are asked to do more and more in their roles. They are data analysts, engineers, economists, epidemiologists, and even meteorologists and geologists. Have the sophisticated tools and amplified processing prowess surpassed the role, or are we finally finding deeper value in this ever familiar but constantly evolving role?
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Moderators:
William VonSeggern
Panelists:
Betsy Hawley, Zack Schmiesing, Roger Pare
New Advances in Commercial Lines Pricing for Fire, Theft, Vandalism & Liability Losses
Commercial lines carriers often struggle with pricing policies based on their own experienced losses due to low density of information available. External data elements can help significantly in making objective, actionable pricing decisions with confidence. Many models of commercial lines risk of fire, vandalism, crime and flood risk have been built through the years. Yet the emergence of big data brings new insights and models invite modification when new knowledge is available. This session will discuss how established models can be improved with big data.
In this session, participants will:
• Be introduced to ultra high precision data and geospatial analytics.
• See the 11 billion points of crime risk via visually engaging maps showing illustrative carrier losses and pricing adjustments recommended by geospatial maps.
• Visualize adverse selection firsthand on the map.
• See the predictive power of the data against illustrative carrier commercial ines data.
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Panelists:
Howard Kunst, Corey Simons
New Predictive Models for Fire Loss Mitigation
Property losses are typically experienced from three main sources (catastrophe, equipment failure and human behavior). Fire consistently ranks as a top-two property loss type for home and commercial lines of business. Many models of fire risk have been built through the years. Yet the emergence of big data brings new insights and models invite modification when new knowledge is available. This session will discuss how established models can be improved with big data.
In this session, attendees will:
• Learn a new approach to identifying addresses at highest risk of fire losses.
• See how behavior is underweighted in current property predictive models.
• See the lift these new models provide on top of over 20 predictors currently in use by carriers to predict fire losses (multivariate double lift plots shown).
Source:
2015 In Focus Seminar
Type:
Concurrent Session
Panelists:
Howard Kunst, Andrew Schiller, John Lucker
