How Do We Impact Decision Making?
This session will discuss recent developments in the field of decision making. The focus will be on how decisions are made, how they should be made and strategies to optimize the use of ERM in the firm decision making process.
Source:
2010 Enterprise Risk Management Symposium
Type:
concurrent
Moderators:
David Ingram
Panelists:
Carl Spetzler
Quantifying Operational and Strategic Risks: An Advanced, Yet Practical Approach
Most ERM programs have suboptimal methods for quantifying operational and strategic risks. Yet industry research shows that they represent more of a threat than financial risks. In this session, you will see new research on the source of risks and review the problems with traditional attempts to quantify operational and strategic risks. You will also learn about an emerging approach (with several case study examples) that companies are using to quantify operational and strategic risks in a way that drives decision-making.
Source:
2010 Enterprise Risk Management Symposium
Type:
concurrent
Moderators:
David Ingram
Panelists:
Sim Segal
A Practical Guide to Creating a Leading Practice Risk Appetite Statement
Taking smart risks while avoiding excessive exposure has been a hot topic in the news since the phrase "subprime meltdown" entered our vernacular in 2007. If the financial crisis has revealed nothing else, it has shown that many organizations are yet to solve this problem. We believe creating a comprehensive risk appetite statement is a prerequisite for sound risk management. Only when firms endeavor to draft a high quality statement, and then clearly communicate this information to risk takers and managers throughout the organization, can they reasonably expect the risk profile to resemble expectations.
While the concept of risk appetite is well understood, many firms still struggle to codify it in a formal statement. In fact, 37% of the financial institutions surveyed in the sixth edition of Deloitte's worldwide Global Risk Management Survey reported that they either have no risk appetite statement, it is informal, or it is not approved by the board. This session will address this problem by describing a practical, step-by-step approach to developing a leading practice risk appetite statement for any industry.
Source:
2010 Enterprise Risk Management Symposium
Type:
concurrent
Moderators:
Dilip Krishna
Panelists:
Terri Dalenta, Mike Batty
Banks and Insurers: Separate Paths, but a Common Destination
The financial landscape evolves throughout time and those who fall asleep during the stable periods are rudely awakened when volatility returns as it has during the past year or so. Enterprise risk management helps, but only if it is implemented with a strong risk culture at its base.
Gain insight from experts in banking, as well as life and casualty insurance, as they share current ERM best practices. Various regulatory entities have encouraged bankers to use company-driven ERM models for financial and nonfinancial risks to determine required regulatory capital. Insurers are using principle-based approaches to develop similar economic-based reserve and capital requirements unique to their business model. ERM implementation is a key component when optimizing results relative to risks taken.
Much has been learned in the recent past about the shortcomings of relying entirely on models. Learn what experts know about modeling and ways to improve modeling processes. You just might discover that models from others in the financial services industry can improve the methods of calculating economic capital, pricing, performance measurement and portfolio management at your company.
A panel of experts, representing various industries and perspectives, will conclude the seminar with a discussion on how challenges have been, and can be, addressed.
Source:
2010 Enterprise Risk Management Symposium
Type:
seminar
Moderators:
Jean-Pierre Berliet
Panelists:
Dan Rosen, Max Rudolph, Gary Tie, Tom Hettinger, Dave Ingram, Lawrence Moews
Keywords:
financial
ERM Model
At the heart of every ERM initiative is one or multiple models. These models attempt to capture behaviors that are by nature unknown and difficult to predict. This one-day seminar will explore techniques required to build a reliable model to capture an array of events and their consequences. The participant will learn how to overcome challenges when building an ERM model. This seminar will have a life insurance perspective and will cover the following topics:
Stress Testing
As the first session of the seminar, time will be devoted to frame the use of models for enterprise risk management, and more particularly for computing economic capital. The session will explore the various realities that are sometime referred as stress testing:
* 99.5% VAR approach through stress on initial conditions used in the context of Solvency II and as described though the four Quantitative Impact Studies,
* sensitivity testing used to understand the impact of misestimating one parameter and thus assessing the model robustness and
* scenario testing or the use of the model to perform what-if analysis.
This session will describe the role of stress test, examine the multi faces of stress testing and will provide attendees with a broader understanding of stress tests.
Model Risk
Are your modeling results trustworthy? This session will cover the controls you need to put in place to ensure the reliability of your model. While this includes SOX-like controls and code peer review, it also includes a deep understanding of the methodology, underlying data, calibration, metrics and the approach used to come to a final answer.
Risk Aggregation
The 2008-09 experience of the financial markets brought to light many failings in projection models, especially in the area of risk aggregation. Are your models adequately capturing the interrelationships between risks-and recognizing that these relationships do not remain static? Using the experience of 2008-09 as a case study, this session highlights the importance of risk aggregation and examines alternative approaches to bring individual risks into an aggregated form, including a comparison of the matrix correlation versus the copula or joint distribution of risks approaches. The session will also consider the different perspectives being taken by insurers and regulators around the globe.
Modeling Customer Behavior
Customer behavior is difficult to model. Its optimality or sub-optimality is the main driver of the results in many cases. This irrational behavior was studied in mortgage pre-payment. This session will examine some techniques to develop valid assumptions that could be transposed to the insurance industry.
This seminar is designed for modelers who have some modeling experience and who wish to learn more and for practitioners who wish to gain insight into the wide range of practices utilized in their industries.
Source:
2010 Enterprise Risk Management Symposium
Type:
seminar
Moderators:
Jean-Pierre Berliet
Panelists:
Alexander Shipilov, Sylvie Hulin, Mark Scanlon, Tony Dardis, Simon Vaysman, Theresa Resnick
Keywords:
ERM
ERM Fundamentals and Practices
The recent financial crisis has highlighted the need for ERM. This one-day seminar examines all aspects of ERM, but from a practitioner's point of view. In doing so, the participants will gain insight into the fundamental underpinnings of ERM, while at the same time learning more about the challenges and successes organizations have had in implementing their programs. The following topics will be covered:
Risk Governance
Leaders will cover typical approaches to ERM governance and offer their perspectives on the challenges organizations have faced in implementing and executing their frameworks. They will address the key issues of risk ownership, risk management and risk monitoring responsibilities. It's not enough to create structure; there must be a creation of a culture and a willingness to identify and address exposures. In addition, leaders will discuss approaches to creating the right culture and the importance of senior leadership support.
Source:
2010 Enterprise Risk Management Symposium
Type:
seminar
Moderators:
Judy Wong
Panelists:
Kevin Madigan, Sim Segal, Terri Dalenta, Howard Rosen, Craig Raymond, Edward Grau
Keywords:
ERM
Model Validation Techniques
Modern computing power has greatly enhanced the complexity of statistical models that one can attempt to fit to observed data. Used in an indiscriminate fashion, almost any statistical technique can end up modeling noise, resulting in a model that fits the observed data well but predicts poorly.
This session will discuss validation (including cross-validation) techniques that can and should be applied regardless of the underlying statistical model employed. One key goal of these straightforward techniques is to avoid models that "overfit" the observed data and thus will not generalize well to future experience.
In addition, the bottom-line question, "How well do GLMs fit?" will also be discussed. Much work can be done to improve the fit of a GLM, but despite even the best efforts, when (if ever) can you be satisfied with a certain level of error?
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Kevin Mahoney, Peng Shi
Understanding the Benefits and Quantifying the Success of a New Rating Plan
Good project management is essential to the success of any rating plan rollout. This requires a quantification of the expected benefits of the ratemaking strategy prior to implementation and a postimplementation review to judge the quality of the new program. Traditionally, actuaries have done little in quantifying the expected success of a new rating plan-especially as it relates to quotes and renewals. In addition, even less analysis has been performed to retrospectively gauge the success of the implemented program. This session will discuss various strategies and metrics that have been used to measure-both prospectively and retrospectively-the success of a new rating plan.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Germain Denoncourt
Pricing Strategy and Risk Management
Since the emergence of predictive modeling in insurance pricing, the industry has re-learned the lessons of how pricing strategy can make or break a company. The ability to forecast the impact of pricing decisions is more important than ever. These forecasts must consider many elements of the dynamic marketplace, including competitive and customer retention/conversion effects. Forecasts of these elements are inherently uncertain. During this session, we will draw on risk management approaches, discussing how we can use uncertain information to make better and more robust strategic decisions.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
A. Cummings
Personal Lines Pricing Strategies
Pricing strategies for personal insurance in the United States differ from those of other consumer products because of both regulation and the stochastic nature of insurance losses. Due to the evolution of personal lines pricing with its origins in the era of pencil-and-paper statistics, there is often a gap between actuarial cost-plus projections and the prices actually charged for personal insurance. As the field has evolved, new techniques have been introduced from academia, other industries, and business contexts. This presentation will be a panel discussion of the evolution of pricing, encouraging audience participation and interaction. Parallels will be drawn between innovations in personal lines pricing strategies and the integration of ideas from statistics, data mining/machine learning, and marketing science. Particular focus will be given to the use of scorecard models for refined pricing and underwriting, as well as the steps involved in integrating demand modeling and price optimization into the pricing process.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Michael Greene, Jose Trasancos
Conversion and Retention Modeling
Predictive modeling has gained widespread acceptance within the U.S. insurance industry as a means to estimate loss costs. However, the U.S. insurance industry lags behind other industries in the use of predictive modeling as a means to understand customer response.
This session will cover the use of multivariate techniques to study and predict outcomes such as response rate, policyholder retention, and new business conversion. The panel will provide practical tips and illustrative results associated with modeling customer response data. Furthermore, the panel will address the benefits and applications of modeling customer response, tying it in at a high level with price optimization techniques.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Geoffrey Werner, James Tanser
Logic, Fallacies and Paradoxes in Risk/Profit Loading in Ratemaking: A Socratic Dialogue
Imagine that the myriad prescribed methods for developing and justifying profit and contingency loads in various regulatory domains have been eliminated. We, the actuarial community have been given the opportunity to erase the entire "white board" of rate regulation as it pertains to fair rates of return in rates and premiums and start from scratch. State regulators have asked us to devise an actuarial approach that should be used by ratemakers in all states for calculating and justifying the profit provision components of indicated premium. How would we rewrite the white board? What would it look like? Would it be any different from what currently exists in regulatory ratemaking procedures? What if we were not held to edicts such as "Thou shalt use discounted cash flow or internal rate of return or these accounting models" when considering "risk and return" aspects ratemaking? In this session, we will discuss how to best use risk metrics, incorporate the different philosophies of "capital appropriation to line" techniques, and address correlation and parameter risk considerations. Is there a true market value to consider and how is it best measured? How is the time value of risk reflected? These and many other topics will be covered and structured as a Socratic dialogue among the moderator, panelists, and audience.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Louise Francis, David Appel, Richard Derrig
Usage Based Insurance: Are you Ready?
Usage-based Insurance (UBI) refers to auto programs that incorporate insureds' driving behavior using data collected from telematic devices for the purposes of differentiating risk and/or providing useful information to policyholders. UBI is poised to be the next major innovation since auto insurers began using credit scores. In fact, several major auto insurers are already using telematics in the United States to verify miles driven, measure driving habits for rating, provide safety services, or some combination of the three.
This session will cover:
1. What is currently happening with respect to Usage Based Insurance?
2. Why is Usage Based Insurance good for companies? For customers? For society?
3. What are the obstacles to implementation?
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
Robin Harbage, Pamela Kramer
Helping a Company Achieve Its Commercial Lines Underwriting Goals Through Predictive Analytics
The underwriting decision is the province of the underwriting department. Underwriters make their decisions based on a myriad of facts, data, analyses, business considerations, and experience. Oftentimes there is a matrix of decision rules to guide the underwriter in making the final decision. During the decision-making process, intuition can play a big role for the underwriter. However, overreliance on intuition and on legacy rules and judgmental overrides can lead to suboptimal decision making. This presentation will make a case for integrating predictive models into the judgmental underwriting process, touching on topics such as cognitive decision traps often made within the realm of judgmental reasoning, the advantage of a statistical "feedback" loop, and the benefits of dimensionality reduction and decision consistency. The presentation will also highlight model development using case study examples and point out a few mistakes that can commonly occur during a modeling project as well as how to address them. Finally, an example of an underwriting decision scorecard with business rule overlays will be discussed.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Greg Taylor
Panelists:
Gaetan Veilleux, Joel Appelbaum
Pricing Strategy and Risk Management
Since the emergence of predictive modeling in insurance pricing, the industry has re-learned the lessons of how pricing strategy can make or break a company. The ability to forecast the impact of pricing decisions is more important than ever. These forecasts must consider many elements of the dynamic marketplace, including competitive and customer retention/conversion effects. Forecasts of these elements are inherently uncertain. During this session, we will draw on risk management approaches, discussing how we can use uncertain information to make better and more robust strategic decisions.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
A. Cummings
GLM II
GLM I provided the case for using GLMs and some basic GLM theory. GLM II will be a practical session outlining basic modeling strategy. The discussion will cover topics such as overall modeling strategy, selecting an appropriate error structure and link function, simplifying the GLM (i.e., excluding variables, grouping levels, and fitting curves), complicating the GLM (i.e., adding interactions), and validating the final model. The session will discuss diagnostics that help test the selections made.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Margaret Milkint
Panelists:
Ernesto Schirmacher
Handling High-Dimensional Variables
Generalized linear modeling has become the standard technique for predictive modeling within the insurance industry. There are some variables that have a large number of levels; oftentimes, these variables may have relatively few exposures. It is important to consider some advanced techniques when handling such variables.
This session will discuss special techniques for handling high-dimensional variables, with a focus on territory boundary analysis, vehicle symboling, and workers compensation classes.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Margaret Milkint
Panelists:
Klayton Southwood
GLM I
Do terms such as "link function," "exponential family," and "deviance" leave you puzzled? If so, this session will clarify those terms and demystify generalized linear models (GLMs). The session will provide a basic introduction to linear models and GLMs. Targeted at those who have modest experience with statistics or modeling, the session will start with a brief review of traditional linear models, particularly regression, which has been taught and widely applied for decades. Session leaders will explain how GLMs naturally arise as some of the restrictive assumptions of linear regression are relaxed. GLMs can model a wide range of phenomena including frequencies and severities as well as the probability that a claim is fraudulent or abusive, to name just a few. The session will emphasize intuition and insight rather than mathematical calculations. Illustrations will be presented using actual insurance data.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
Margaret Milkint
Panelists:
Ernesto Schirmacher, Ashley Lambeth
Catastrophe Modeling Workshop: Concurrent Session B
This session assumes the mechanics of generating the results have been dealt with and focuses on the implications of the various results for a company's operations, financial results, reinsurance program, etc. Some of the issues involved in allocating the rate need indicated by the model to lines of business and territory will be considered.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
James Donelon
Panelists:
Shawna Ackerman
Catastrophe Modeling Workshop: Concurrent Session A
This session looks at the various concepts and formulas that are used in a discussion of catastrophe modeling. Terms such as AAL, PML, EP, TVAR, will be explained. The session will focus on the formulas, the mechanics and the pitfalls in the preparation of these values. In particular, we will examine how results from a catastrophe model can contribute to a rate indication. We will consider how catastrophe modeling results can be used and misused in a rate filing.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Moderators:
James Donelon
Panelists:
M. Parsons
Product Development Workshop Part 6: Product Monitoring/ Risk Management
Just because the product is up and running does not mean that the product manager's job is done. Learn how the product profitability is managed and what risk flags will alert when something is amiss. Participants will also discuss what the early indicators of success are.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
Curtis Parker
Product Development Workshop Part 5: Marketing
Designing a product is one thing but if you can't get it to market then it is worthless. Facilitators will discuss what the marketing issues are and also explain how to measure marketing effectiveness.
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
Mark Crutcher
Product Development Workshop Part 4: Regulatory
Depending on the product, the regulatory concerns can be substantial. During the session these key questions will be discussed: Is the company making a new filing or revising a current one? What is the impact on the customers? Will the change improve the potential for more customers to be written, thus reducing state pools? How were rates substantiated?
Source:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
Steven Armstrong, Eric Huls
Product Development Part 3: 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:
2010 Ratemaking and Product Management Seminar
Type:
concurrent
Panelists:
Frank Palmer
Actuarial Professionalism
Mark and Heather will sharpen our professionalism skills with an informative and exciting extended session.
Source:
2010 Regional Affiliate - CANW
Type:
affiliate
Panelists:
Mark Phillips, Heather Caffoe
Keywords:
Professionalism