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.
Comparison of Linear and Logistic Regression for Insurance Segmentation Models
For Insurance predictive modeling applications, we often deal with cases where we try to predict the true outcome of an event, such as occurrence of a claim, identification of a fraud, ultimate development of a claim severity. In such cases, statistically speaking, given the specific target variables, we perform logistic or General Session GLM regression. However, more often than not, we can approach such prediction using a segmentation approach by ranking observations based on the predicted values from the lowest to the highest. One of the most popular segmentation models is a credit score model, of which the better the credit score, the better the risk. In this presentation, we show that for segmentation model or scoring model, the segmentation result is not sensitive to the underlying distribution assumption. For applications with a binary target variable, the linear regression would yield segmentation results that are very close to what Logistic regression yields. Using historical claims data from a couple of Insurance companies, we will show that the segmentation obtained from both methods would be very similar. More importantly, we will prove theoretically that the coefficients of the independent variables obtained from both the methods would have the same sign and that for the case when there is only one independent variable, the ranking of observations based on the predicted values obtained from both the methods is exactly the same. We will also discuss important implications of such finding for the insurance predictive modeling applications.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Gerry Kirschner
Panelists:
Kranthi Nekkalapu, Debashish Banerjee
Commercial Usage Based Insurance
Making the business case for a telematics application in commercial lines is easier than personal lines. Surprisingly, the majority of successful product offerings in the insurance industry are in personal lines. Nevertheless, commercial auto insurers are moving quickly to catch up with personal auto insurers. In this presentation, we will contrast personal and commercial lines needs. We will discuss Usage Based Insurance (UBI) strategies that worked for personal lines and why they do not work in commercial lines. Finally, we will focus on how to build a strategy for your commercial UBI offering that is aligned with your customer needs and your company’s long term goals.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Gerry Kirschner
Panelists:
Erin Bellott, Mohamad Hindawi
Building a Data Driven Culture: Optimizing the Change Management and User Adoption Process during and after Predictive Analytics Implementation
Once you introduce predictive analytics into your organization, the journey begins to becoming more data-driven and incorporating new tools to make underwriting decisions. It’s important to address how predictive models are designed to work in combination with an underwriter’s expertise. This roundtable discussion will allow participants to share lessons learned as best practices, as well as provide practical steps you can take to address the important issue of adoption.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Gerry Kirschner
Professionalism in the Evolving World of UBI
The emergence of usage-based auto insurance (UBI) is challenging actuaries to make decisions based on sparse or heterogeneous data in order to get their programs to market. UBI also often involves predictive modeling, with some models requiring expertise beyond traditional actuarial subject matter (e.g., traffic safety). Finally, UBI model realizations may not align precisely with how actuaries traditionally envision risk classification. In this session we will evaluate how the actuarial principles and standards of practice apply to various elements of professionalism in the evolving world of UBI.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Panelists:
Jim Weiss
Product Portfolio Optimization
Leading property and casualty Insurers are optimizing and innovating product portfolios to enable top-line growth and profitability. Streamlining existing products and introducing new products have become a critical path to growth in the current marketplace. In this session, the panelists will discuss the key challenges in optimizing their products and how leading practices address the challenges. The panelists will also support the discussions with several case studies.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Joshua Youdovin
Panelists:
Rita Zona, Erin Kang
Product Development: From Conception to Execution
This session will illustrate the product manager’s role in developing new product offerings, as well as measuring and monitoring performance once such products are in place. Topics to be covered will include an overview of “agile project management”, making use of new technology such as (at present) smart phones and tablets, problem solving, and, when necessary, implementation of corrective actions.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Joshua Youdovin
Panelists:
Scott Drab, Becky Lester
Product Development Workshop - Part VII: Product Monitoring
After the product has been designed and is being sold in the marketplace, our focus needs to turn to its performance. Participants will discuss early indicators of a new product's success.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Donald Hendriks
Product Development Workshop - Part VI: Marketing
If a tree falls in the forest but no one hears it, does it make a sound? Likewise, if a product is designed but doesn't get to market, has a product really been developed? Participants will discuss marketing issues and ways to measure marketing effectiveness.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Kelly McKeethan
Product Development Workshop - Part IV: Governance
New products are important to an organization's continued growth and marketplace relevance. What processes and governance should companies consider in terms of approving new products? What role (if any) do senior management and the board have in shaping and bringing forth new products? Speed to market is not always a predictor of success in managing products. This session will provide a perspective on how to achieve speed to profit through effective project selection, prioritization, and execution. We will also discuss the factors that contribute to success in launching new products and leading practices based on research and practical experience.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Kelly Cusick
Product Development Workshop - Part III: Product Design
Attendees for this session will explore the different considerations for the product design. Panelists will cover elements of pricing, claims, legal, marketing, operations, and IT.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Robin Harbage
Product Development Workshop - Part II: Data Gathering
Understanding your data is very important. It will dictate your ability to understand the profitability of the product, as well as market potential. Participants will explore various topics including starting from scratch vs. mimicking a competitor, learning what data sources are available and how you can get your hands on them.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Brett Nunes
Predictive Modeling Data Prep Best Practices
Let’s talk predictive modeling data preparation best practices and standards. We will start with an overview of data preparation for the predictive modeling process, review the relevant actuarial standards of practice, and outline the quality control steps.
The second half of the presentation will deep dive into validating the data used, so that the resulting output is accurate. The selection and validation of input data is based on currency (how recent the data is), timeliness (how frequently it is updated), granularity (how detailed it is), and accuracy (how much error is acceptable). The final and most important aspect of the input data is relevance, which is an indication of what each variable contributes to the final risk analysis. Since hazard modeling is designed to replicate natural environmental processes, it is often necessary to include multiple varied inputs from different sources. Ensuring that all of the input data works symbiotically is necessary in order to provide a clear and accurate assessment of modeled risk.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Jeremy Smith
Panelists:
Howard Kunst, Thomas Jeffery, Peggy Brinkman
Propensity Score Methods for Evaluating Insurance Pricing Strategies
The designed experiment with a randomly selected control group is the gold standard for evaluating competing alternatives. However, formal experimentation is frequently infeasible, whether due to ethical, legal, or practical considerations. It is for such situations that propensity score methodology was developed. Propensity scores adjust observational (non-experimental) data to, in essence, match “cases” and “controls” that would have likely occurred in a designed experiment. They can be used in any statistical analysis that would have resulted from a formal experiment. In this session, using North American insurance pricing constraints, we will illustrate how propensity scores can be utilized to conduct a pseudo-experiment where pricing strategies are evaluated against a control.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Jeremy Smith
Panelists:
Reuven Shnaps, David Whiting
Bringing Emerging Issues To Market - ISO's Commercial Lines Program Initiatives
Carriers recognize the importance of monitoring emerging trends for potential impacts on business. While identifying and analyzing trends is critical, translating those trends into new products can be a challenge. This session will explore several recent enhancements that the Insurance Services Office (ISO) has introduced to its commercial lines insurance programs, including: • Cyber Risk Liability - Cyber losses routinely make the headlines, and cyber liability is consistently identified as one of the leading risks facing business today. ISO's E-commerce program was designed specifically to address this important and growing exposure.
• Medical Data Privacy - fundamental shifts in health care delivery, coupled with statutory requirements related to patient data, have sparked a growing demand for data privacy coverage for health care professionals. Changes are coming to ISO's medical malpractice program.
• Car Sharing Services - Interest in car sharing, from a commercial enterprise perspective as well as individuals, has changed the face of certain auto risks. Learn what changes ISO has made to address this topic.
• Mobile Equipment Business Interruption - Today's business is more mobile than ever, with some commercial enterprises deriving significant income from operations that are conducted away from a traditional "brick and mortar" location. Enhancements are being introduced under multiple lines of business to allow for underwriting flexibility.
• Commercial Property Rating - Many refinements have been made to rating algorithms for commercial property over the last few years. From new limit of insurance rating, to enhanced wind rating and changes in the public protection classification structure, these changes are designed to improve the predictive nature of ISO pricing.
ISO's product development professionals will review these changes, as well as some of the special considerations that needed to be evaluated during the product development process.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Jeremy Smith
Panelists:
Joseph Palmer, Ron Beiderman
Big Data and Data Science: Differences and Technologies
We start by discussing the definitions of the catch phrases “big data” and “data science.” We explore the differences between data science, predictive analytics, machine learning, data mining, and statistics. We discuss the technologies and skills currently used to manage and analyze big data and their limitations. We then explore the implications of big data in an insurance context and discuss the challenges and opportunities for insurers using big data in areas such as marketing, risk analysis, and claim fraud. We argue that data does not need to be “big” to be valuable - massive amounts of data are not always necessary to benefit from predictive analytics.
Source:
2014 Ratemaking and Product Management Seminar
Panelists:
Peggy Brinkmann
Basic Ratemaking Workshop: Ratemaking Relativities
This session will examine the various methods that actuaries use to allocate overall average rates to various subdivisions of a line of business, including territories, classifications, and tiers. Some of the methods discussed will consist of univariate, multivariate, and General Sessionized linear modeling techniques.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Chris Cooksey
Basic Ratemaking Workshop: Large Account Pricing
This session will examine the differences between large accounts and small accounts, and how they can and should be treated differently from an insurance pricing perspective. Participants will be introduced to pricing methods that both utilize the increased credibility of large account experience and recognize the uniqueness of each risk. Specifically, this session will serve as an introduction to experience rating, schedule rating, and retrospective rating.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Josh Taub
Basic Ratemaking Workshop: Introduction to Increased Limit Factors
This session will present an overview of increased limits ratemaking. Participants will cover General Session concepts, such as calculating limited average severities, and practical problems with developing increased limit factors (ILFs) from a distribution of loss data. The session will also provide an overview of excess and deductible pricing and will discuss common approaches for calculating ILFs.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Jared Smollik
Basic Ratemaking Workshop: Exploring the Fundamental Insurance Equation
The fundamental insurance equation is the foundation of the ratemaking process. This session will include techniques for adjusting historical data to estimate its various components (premiums, losses, expenses, and profit) in the relevant pricing time period. The session will conclude by briefly exploring other considerations company management should make, along with the cost-based rate indication derived from the fundamental insurance equation, to determine what rates to charge in practice.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Workshop
Moderators:
Jeremy Smith
Panelists:
Eric Schmidt
Avoiding Personal Auto Fraud at the Point of Sale
Most efforts to stem the rising tide of auto insurance fraud are after a loss occurs, when it is more difficult and costly to investigate and resist potentially fraudulent claims. Identification and mitigation of fraud is best performed at point of sale PRIOR to policy issuance. Once a fraudster is a policy holder, they win, as they know that carriers would rather settle than incur the cost of litigation and lost time of scarce carrier resources.
This session will demonstrate how, through the quantification of human behavior as it relates to the process of applying for insurance, measuring the accuracy, honesty and willingness to disclose enables insurers to identify and remediate (or avoid) applicants with the highest probability of submitting fraudulent claims. This process measures and mitigates both "hard fraud" (as it relates to physical damage and bodily injury claims) and "soft fraud" (as it relates to deficit premiums due to the non-disclosure of exposures or misrepresentation of key underwriting variables).
The session will review the process, methods and mathematics used in the study and the detailed findings associated with the study of more than 3 million auto policies and their associated claims (both real and fraudulent) associated with those policies. This method results in a high correlation between the accuracy of the information provided on the application (by the carrier OR agent) and the first term loss ratio associated with these policies.
The session will also include a review of a composite of subsequent recent case studies involving carriers that were not part of the original data set. Based on a recent study, less than half of insurers surveyed are using technology for “non-claims functions”. This session will describe how carriers can enhance their anti-fraud efforts by intervening in the sales and underwriting process. Pushing back on a small percentage of these "fraudulent" applications can result in significant loss avoidance as well as additional premium capture as the carrier's realize and are able to measure the true risk that a consumer represents.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Jeremy Smith
Panelists:
John Petricelli
Autonomous Vehicles and the Impact on the Insurance Industry
The National Highway Transportation Safety Administration estimates that, of the crashes that result in over 30,000 fatalities each year in the US, over 90% are due at least in part to human error. Consequently, the opportunity offered by self-driving cars, to "remove" the human from that equation, represents an incredible opportunity to improve the safety of our nation's highways.
However, such a change also represents a significant challenge to the way we regulate our highways, as nearly all laws and regulations presume a human is responsible for the safe operation of the vehicle. As we move from an operation based upon a human responding to an environment they observe, to an operation where a machine responds to data it records, how that data will be handled and used is a large and currently unresolved question. For the insurance industry, this data provides an opportunity to improve the fairness and accuracy of rate setting and liability determination, but questions regarding location tracking and secondary markets for this data could prevent realization of this benefit. This panel will discuss these technical opportunities, the political and legal risks, and suggest some guidelines for moving forward in this "brave new transportation world."
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Steven Groeschen
Panelists:
Robert Peterson, Michael Stienstra, Frank Douma
And the Winner is…? How to Pick a Better Model
You have just finished running some data through a predictive modeling package. Now all you need to do is summarize the results, send them along, and you’re done, right? WRONG. At the absolute minimum, the modeler should understand and demonstrate the goodness-of-fit of the model. In most cases, the modeler should also prove that the constructed model provides lift over the existing rating structure. After all, what good is a new model if it cannot outperform the competition?
In this session we will explore, in significant detail, three often-overlooked components of the modeling process: measuring goodness-of-fit, assessing lift, and internally validating a predictive model. Model development usually is a major investment. We should make sure our models are performing well in order to get the best
bang for the buck!
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Steven Groeschen
Panelists:
Hernan Medina, Dan Tevet
Analytics & Regulation, Beyond GLMs
Departments of insurance throughout the United States have had a couple of decades to determine their opinions on and requirements for filed rates based on GLMs. Now they are being faced with a variety of analytical techniques, some of which approach the data in entirely novel ways from GLMs, and the complexity of many of these models far surpass GLMs. This session will present both a regulator’s and modeler’s perspective on advanced analytics and the regulatory environment.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Nancy Arico
Panelists:
Cara Blank, Chris Cooksey, Kathryn Koch, Glenn Hiltpold
Allocating/Attributing  Capital- A Hands on Exercise
A laptop is recommended for participation in this session.
Join us for a hands on technical session where the audience will be charged with an exercise in allocating capital to lines of business considering various methods and will be working in groups to make strategic recommendations based on their respective results.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Nancy Arico
Panelists:
Robert Wolf
Actuarial Techniques in a Non-Insurance World
Among other things, actuaries specialize in working with data, developing forecasts, and building models which then help guide business decisions. Consequently, actuaries and actuarial techniques are increasingly being employed in non-traditional functions, such as claims analytics, marketing, and risk management. As we become a more data-centric culture, there is a great opportunity to apply these techniques to solving problems outside of insurance.
Source:
2014 Ratemaking and Product Management Seminar
Type:
Concurrent Session
Moderators:
Nancy Arico
Panelists:
Frank Chang, Loren Nickel
