Casualty Actuarial Society

2017 Ratemaking and Product Management Seminar & Workshops

Meeting Presentations

BII-1: Evolution in Technology and Demographics: An Impact on the Insurance Industry

Download Presentation

Homeowners and Auto insurance are evolving in response to technological advancements and demographic changes. We will start with an overview of the evolution of insurance including how technology impacts the way we capture insurance exposure for homeowners and auto and how it impacts rates. We will then shift to the impact of the autonomous vehicle on insurance, then latest advancements in connected home products and potential impacts for insurance companies.

    Moderator:
    Sheri Scott, Milliman
    Speakers:
    Sheri Scott, Principal & Consulting Actuary, Milliman
    Thomas Smith, President, Senteri

BII-2: Wellness Data: The Next UBI?

Download Presentation

Sleeping on the job has never been a fast track to success, but sleeping on the way to the job may lead to an early and unscheduled retirement. Research found that more than one-in-five fatal car accidents in the United States involves a drowsy driver.

P/C insurers have long offered discounts to policyholders who attend defensive-driving courses or submit to telemetric examination of their driving habits with usage-based insurance (UBI) devices. Unfortunately, those approaches achieve only limited success because they focus on behaviors surrounding the insured asset, and not a policyholder's larger decisions about wellness. A more effective approach might address how to minimize underlying risk factors that cause or contribute to P/C losses.

This session will bring various perspectives on the relationship between "Wellness Data" and property and casualty risk, and illustrate how P/C insurers may take a nod from life insurers and potentially apply modeling to new data sources such as wearables to help improve underwriting and marketing.

    Moderator:
    Dion Oryzak, Insurance Solutions
    Speakers:
    Chris Stehno, Managing Director, Deloitte Consulting, LLP
    Dion Oryzak, Insurance Solutions

BII-3: UBI Smartphone Apps: What's Hot and What's Not?

Download Presentation 1
Download Presentation 2

We have seen a proliferation of usage-based insurance (UBI) programs in recent years. Many of these use data collected with OBDII devices, but there has been an increase in activity on smartphone apps. Apps bring the promise of rich data at a low cost, but is this data source the real thing or too good to be true?

In this session, we will cover:

  • How mobile apps are capturing driving data for UBI purposes
  • What types of data can be captured, and how it differs from OBDII data
  • The way mobile telematics apps complement connected cars to accelerate UBI adoption
  • Trends in smartphone UBI programs
  • A case study of a recent smartphone app implementation
Learn what is working and what is not with smartphone UBI.
    Moderator:
    Peggy Brinkmann, Principal & Consulting Actuary, Milliman
    Speakers:
    Peggy Brinkmann, Principal and Consulting Actuary, Milliman
    Ryan Morrison, CEO, True Mileage, Inc.
    Jim Levendusky, VP, Telematics, Verisk Analytics
    Jamie Cox, Vice President, True Mileage, Inc.

BII-4: Evolution in Business Models for Insurance

Download Presentation

InsureTech companies are flooding the landscape of the insurance industry. These innovators seek to challenge traditional business models for insurance, leveraging advancements in technology and creative thinking to deliver new products and differentiated levels of service to customers. In this session we will hear from InsureTech companies who are shaking up the insurance landscape, exploring new business models for the sharing economy and peer to peer insurance, and consider the implications of these innovations on the actuarial community.

    Moderator:
    Kelly Cusick, Senior Manager, Deloitte Consulting, LLP
    Speakers:
    Kelly Cusick, Managing Director, Deloitte Consulting, LLP
    Michael Fitzgibbon, Chief Underwriting Officer, Slice Insurance Technologies Inc.
    John Peters, Chief Underwriting Officer, Lemonade Insurance Company

BII-5: Telematics & IoT: Proactive Protection Changes the Insurance Ecosystem

Download Presentation

Many insurers want to change the conversation with their customers while increasing engagement and satisfaction. By leveraging sensor data, insurers can take on the burden of worrying about the care and wellbeing of the customer's vehicle or home. Proactive protection services can assist with tasks such as:

  • Auto repairs
  • Property loss prevention/maintenance
  • Recommendations for safer driving routes, parking locations
The Internet of Things is generating the data and the insights for insurers to offer these services and enhance customer satisfaction. During this session you will learn more about how proactive protection services can help both your customers and your company mitigate risks and reduce losses.
    Moderator:
    Jim Weiss
    Speakers:
    Adam Waldron, CIO, Farm Bureau Insurance of Idaho
    Dawn Mortimer, AVP IoT/Telematics Claims Product Development, Verisk Insurance Solutions

CL-1: 3D Printing: Hype or Reality?

Download Presentation

There is no doubt that 3D printing is a very exciting technology, but what is it really all about? Is it as revolutionary as people say? We'll talk about what it is and why so many people are excited about it, including its application in various industries. This technology will impact society, business, our personal lives and the insurance industry. Come find out how and get a glimpse of the future.

    Moderator:
    Tong Xu, Actuary, The Travelers Companies, Inc.
    Speakers:
    Tong Xu, Actuary, The Travelers Companies, Inc.
    Robert Weireter, Senior Underwriter, Swiss Re

CL-2: Beyond UBI – Commercial Insured Usage Data as a Customer Added Value

Download Presentation

This session will explore ways in which data collected from commercial insureds may be used to provide added services such as expense reduction to the insured while also allowing insurers to assess risk and pricing as well as reduce claims. Examples include automobile fleet monitoring as well as water flow and electrical usage monitoring in commercial buildings.

    Moderator:
    Damon Lay, Director, Farmers Insurance
    Speakers:
    Damon Lay, Director, Farmers Insurance
    Jacob Rothfuss, Head of Commercial Property, Liability, and Auto, Farmers Insurance Group
    Daniel Sterling, Founder & CEO, Water Hero, Inc

CL-3: Businessowners Policies in the Big Data Era

No presentation available for download

The era of big data and analytics has fundamentally changed the goals, business models, coverages and premium determination methodologies for small commercial multiple peril and businessowners policies (BOPs). This session will examine these changing influences and how leading BOP writers are adapting.

    Moderator:
    Lin Xing, ISO
    Speakers:
    Lin Xing, ISO
    Robert Walling, Principal & Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Thomas Kolde, Consulting Actuary, Pinnacle Actuarial Resources

CL-4: The Competitive Weapon: Alignment of Analytics and Commercial Underwriting

Download Presentation

The interplay of predictive models, rate order calculations ("ROC"), rules, and risk appetite with field personnel knowledge is critical for a successful deployment of a predictive model to any part of the value chain. This is particularly true for commercial lines underwriting due to the latitude given to underwriters in applying schedule debits and credits and the resulting impact on premium.

In our session we will discuss typical challenges with an emphasis on active field involvement and participation throughout the process. The qualitative side will be illustrated with an industry case study narrative that speaks directly to the advantage of creating alignment of model scores, ROC, firing of rules, and quality of account knowledge as defined by the field. The quantitative side will illustrate the challenges of knowledge engineering and how to blend with data-driven decision making. The discussion will highlight choices made to incorporate field input and achieve "last mile" success.

The session is designed to feature a moderated dialog with the participation of an industry leading executive who is wrestling first-hand with the challenges of commercial lines modernization. Audience participation is encouraged.

    Moderator:
    Pam Sealand Reale, AVP and Actuary, The Hartford
    Speakers:
    Pam Sealand Reale, AVP & Actuary, The Hartford
    Gary Ciardiello, Principal, EY
    Christine Heiderich, Underwriting Specialist, Pinnacol Assurance

CL-5: Where Cyber Security Meets Insurance: Challenges Presented and Opportunities Created

No presentation available for download

This session features a panel discussion offered by keynote speaker and former FBI agent Eric O'Neill, and Symantec Senior Principal Actuary Joshua Pyle. Panelists will discuss a series of interesting and timely questions pertaining to the dynamic cyber peril, including "What is the biggest cyber security risk in 2017?" and "What are the most significant challenges to successfully and confidently writing cyber insurance?" Please feel free to bring your own questions or simply come to enjoy the inspiring discussion.

    Moderator:
    Anita Sathe, CoverHound Insurance
    Speakers:
    Joshua Pyle, Senior Principal Actuary, Symantec
    Eric O'Neill, The Georgetown Group
    Kelli Broin, VP of Product, CoverHound

CL-6: Where Will the Drones Take Us?

Download Presentation 1
Download Presentation 2

The skies are not (yet) full of drones but they are certainly becoming much more popular. Recreational and commercial users are growing in number and the technology is really taking off. We even have some regulations intended to provide some law and order. Imagination and enthusiasm are great and while the insurance industry needs to embrace new opportunities we also need to be mindful of new challenges. This session will bring us up to speed on the world of drones, with particular emphasis on the insurance impacts.

    Moderator:
    Timothy McCarthy, Manager & Assistant Actuary, ISO
    Speakers:
    Robert Weireter, Senior Underwriter, Swiss Re
    Timothy McCarthy, Actuarial Director for Commercial Liability, ISO

CP-1: An Alternative Approach to Credibility for Large Account and Excess of Loss Treaty Pricing

Download Presentation

This paper was recently approved for e-Forum publication by the CAS Ratemaking Committee. It illustrates a comprehensive approach to utilizing and credibility weighting all available information for large account and excess of loss treaty pricing. Excess losses are utilized to modify the severity distribution used to calculate the increased limits factors via a simple Bayesian credibility technique that does not require any specialized software to run. Such an approach considers all available information in the same way as analyzing burn costs, but does not suffer from the same pitfalls.

    Moderator:
    Sandra Callanan, Chief Actuary, Mountain States Insurance Group
    Speakers:
    Sandra Callanan, Chief Actuary, Mountain States Insurance Group
    Uri Korn, Industry Analytics Leader, AIG

CP-2: Removing Bias—the SIMEX Procedure

Download Presentation

This paper was recently approved for e-Forum publication by the CAS Ratemaking Committee. SIMEX (Simulation-Extrapolation) is a very general technique that helps to correct for bias in estimates caused by errors in measurements of predictors. The method is well established in statistical practice, but seems to not be as widely known in actuarial circles. Using ordinary least squares regression as an example, the method is illustrated using some simple R code.

    Moderator:
    Sandra Callanan, Chief Actuary, Mountain States Insurance Group
    Speakers:
    Sandra Callanan, Chief Actuary, Mountain States Insurance Group
    Thomas Struppeck, University of Texas at Austin

DM-1: Demystifying Data Quality Tools

No presentation available for download

Data quality is a primary concern when you perform an actuarial analysis or undertake a predictive modeling project. Top among your concerns would be to review the data for accuracy, reasonability, completeness and consistency. A valid question is: when you write programs to perform data quality checks, are you reinventing the wheel? Perhaps your organization has a commercially acquired data quality tool that can aid you, or perhaps acquiring one may be worth considering. This session provides explanations and examples of data quality functions such as data profiling, entity resolution, pattern analysis, etc., that commercially available data quality tools perform. Even if you or your employer choose not to purchase a data quality tool from a vendor, knowing the kinds of tasks these tools perform can increase your awareness of things to look for with regards to data quality.

    Moderator:
    Jason Smith, ISO
    Speakers:
    Peter Bothwell, VP, Data Science, The Hartford
    Jason Smith, Business Associate Sr., ISO
    Tracy Spadola, Vice President Strategic Data Operations, Verisk Analytics

DM-2: Applying Big Data Analytics in the Insurance Sector

No presentation available for download

As the hype subsides and expectations begin to settle, leading insurers are now discovering tangible value from their big data analytics projects. During this presentation we will set out the tools and processes companies should have in place to expedite value discovery and minimize investment cost in their big data analytics capabilities.

    Moderator:
    Claudine Modlin, Willis Towers Watson
    Speakers:
    Jason Rodriguez

DM-3: CAS Data and Technology Working Party Report

Download Presentation

Members of the CAS Data and Technology Working Party will present findings from their report, which was recently featured in CAS E-Forum. The report discusses how, during the ongoing revolution of data and analytics capabilities, information technology (IT) departments and vendors have embraced "data & analytics," "big data," and "data science" as the new frontier for informed decision-making. In the P&C insurance industry, the CAS actuary is uniquely well-positioned to partner with IT to advance the potential of these disciplines to benefit the industry. In order to be a participant in the conversation, however, the actuary must have knowledge of the language, practices, tools and techniques of the technology supporting this revolution.

    Moderator:
    Jim Weiss, Director, Analytic Solutions, ISO
    Speakers:
    Jim Weiss, Director, Analytic Solutions, ISO
    Peter Bothwell, VP, Data Science, The Hartford
    Dominique Yarnell, Vice President & Pricing Actuary, Aspen Insurance

DM-4: Effectively Evaluating External Data

No presentation available for download

Data is at the core of the ratemaking process. By effectively leveraging new and innovative data sources, companies can out segment the competition and gain competitive advantage. However, anyone who has been through a data evaluation process knows that it is typically as simple as reading the label on the package, tossing it into the cart, and heading to checkout. It is not uncommon for data evaluations to take months and ultimately yield results that are difficult to interpret.

In this session we will share some tips and tricks to make sure you have an efficient and effective data evaluation. There will be a focus on different statistical methods to quantify the business value of adding new data assets. This session will also use live polling so companies can better understand how they compare to their peers on topics like:

  • How many new data sources do you typically evaluate in a year?
  • How long does the typical evaluation last?
  • What business lines benefit the most from the inclusion of external data?
    Moderator:
    Jim Weiss, Director - Analytic Solutions, ISO
    Speakers:
    Jim Weiss, Director, Analytic Solutions, ISO
    Drew Lawyer, Sr. Professional Services Consultant, Earnix

DSPA-1: Bayesian Analysis of Big Data

No presentation available for download

While Bayesian methods have attracted considerable interest in actuarial science, they are yet to be embraced in large-scaled predictive modeling applications, due to inefficiencies of Bayesian estimation procedures. This paper develops an efficient Markov chain Monte Carlo algorithm using distributed computing on a cluster of computers. The distributed algorithm dramatically boosts the efficiency of Bayesian estimation and expands the scope of applicability of Bayesian methods. The empirical analysis applies a Bayesian hierarchical Tweedie model to a big data of 13 million insurance claim records. The proposed algorithm achieves as much as 65 times performance gain over existing methods in this application. The analysis demonstrates that Bayesian methods can be of great value to large-scaled insurance predictive modeling.

    Moderator:
    Cheng-Sheng Peter Wu, Deloitte Consulting, LLP
    Speakers:
    Cheng-Sheng Peter Wu, Managing Director, Deloitte Consulting LLP
    Yanwei Zhang, Senior Technical Actuary, Uber Technology Inc

DSPA-2: Easy Tree-sy: Everyday Applications for Decision Trees

Download Presentation 1
Download Presentation 2
Download Presentation 3

This session will cover the background/theory behind decision trees, their benefits and drawbacks, a demonstration of fitting decision trees with free software, and example applications of decision trees for data exploration, GLM residual analysis, and underwriting analysis.

    Moderator:
    Linda Brobeck, Pinnacle Actuarial Resources
    Speakers:
    Peggy Brinkmann, Principal and Consulting Actuary, Milliman
    Daniel Murphy, Chief, Trinostics LLC
    Linda Brobeck, Senior Consulting Actuary, Pinnacle Actuarial Resources

DSPA-3: Genetic Algorithms with Applications to Insurance

No presentation available for download

A genetic algorithm (GA) is a method for solving both constrained and unconstrained optimization problems based on a natural selection process that mimics biological evolution. We give a general overview of GAs and focus on a few specific algorithms with insurance applications: symbolic regression (modeling continuous responses), text mining (looking for higher order n-grams) and differential evolution (used for rating factor optimization, a problem in which the objective function exhibits multiple local minima).

    Speaker:
    Eliade Micu, Director, R&D, Clyde Analytics

DSPA-4: Tutorial on Open Source Text Mining

Download Presentation 1
Download Presentation 2

In 2010 Louise Francis and Matt Flynn wrote a paper, Text Mining Handbook, describing how to do text mining with open source software. The software used in the paper was R and Perl. As a follow-up to the work described in the paper we will show how to use the current open source tools of R and Python to do text mining. Applications will include analyzing text field from claim data and analyzing survey data. As with the paper, we intend to provide a data set along with code that can be used by attendees to begin working with text data. This is intended to be a practical session. It will introduce some of the basic concepts of text mining and then move on to how to use the tools.

    Moderator:
    Louise Francis, Francis Analytics and Actuarial Data Mining, Inc.
    Speakers:
    Matthew Flynn
    Louise Francis, Consulting Principal, Francis Analytics and Actuarial Data Mining, Inc.

ERCM-1: Business Planning Within a Capital Management Framework

No presentation available for download

As the P&C insurance industry is becoming increasingly more complex and fluid to adapt to the continuous changes in the markets, there is an increasing need for companies to reflect risk within their strategic planning framework. In this session we introduce a capital management framework and explore how a P&C insurance company can leverage this framework to assist management with its business decision-making process including strategic growth, pricing, and portfolio management. By having an integrated risk-based approach towards managing the business, a company is ensured to be better prepared for the future, remain competitive in the market, and ultimately provide value to its customers and shareholders.

    Moderator:
    Robert Wolf, StoneTrust Commercial Insurance Company
    Speakers:
    Robert Wolf, Vice President and Chief Actuary, StoneTrust Commercial Insurance Company
    Berna Beekman, Manager, Deloitte Consulting, LLP
    David Shleifer, Deloitte Consulting, LLP

ERCM-2: Intro to Profit and Contingency Loading in Ratemaking

No presentation available for download

The Standard Ratemaking Formula is R=(P+F)/(1-V-Q), where

    R= Rate per unit Exposure
    P= Loss Cost (or Pure Premium) per unit exposure
    F= Fixed Expense per Unit Exposure
    V= Variable Expense Costs (% premium)
    Q= Profit and Contingency Load (as % Premium)
This session is intended to be an introductory session on how to derive your "Q". There are many methodologies. Some methodologies are mandated by regulation. Some are subject to the actuary's discretion and rationale. Multiple answers can occur given the approaches and considerations in how to best reflect the cost of capital. This session is intended to provide discussions on advantages and disadvantages of alternative approaches.
    Speaker:
    Robert Wolf, Vice President and Chief Actuary, StoneTrust Commercial Insurance Company

ERCM-3: Ratemaking, Product Management, Predictive Analytics — How does it all fit within an ERM Framework?

No presentation available for download

The Business of Insurance operates best under optimal collaboration of Marketing/Product Managers, Underwriters, Actuaries and Data Scientists. There is diverse talent on this team and expertise. There is also, of course, a likelihood of significant diversity of opinions on strategy and direction. The Predictive Models are subject to Model Risk. The Actuary adjusts for bias and credibility of data and considers "Change". Underwriting and Marketing may be at odds as regards incentives.

Most of the risks that potentially manifest are based on the decisions of human beings who are biased with their perspectives within their respective domains and incentives. Within an ERM perspective, how can one best align authority for decision-making with ultimate accountability among this Team of Experts? These considerations, and more, will be be discussed in the this session.

    Moderator:
    James Guszcza, US Chief Data Scientist, Deloitte Consulting, LLP
    Speakers:
    Kimberly Holmes, Global Head of Strategic Analytics, XL Catlin
    James Guszcza, US Chief Data Scientist, Deloitte Consulting, LLP
    Christopher Monsour, VP & Actuary, Predictive Business Applications, CNA Insurance Companies

ERCM-4: Introduction to Sustainable ERM

No presentation available for download

This Session is intended to provide an update on the work of the CAS Working Party on Sustainable ERM. 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. This session will show evidence for a global Sustainability meta-trend and provide examples and best practices for insurance companies. It will directly serve the risk professionals with relevant, current and practical information on the new way of doing business and integrating Sustainability into ERM.

    Moderator:
    Brian Brown, Milliman, Inc.
    Speakers:
    Sandra Callanan, Chief Actuary, Mountain States Insurance Group
    Fan Yang, AIG Brian Brown, Principal and Consulting Actuary, Milliman, Inc.

GS-1: Cyber Security

No presentation available for download

Eric O'Neill will discuss Cybersecurity in the Age of Breaches and Espionage (political and corporate). Mr. O'Neill will also provide in-depth coverage on how the insurance industry (and actuarial roles) are impacted by Cybersecurity policy, practices and some tips for prevention.

    Moderator:
    Amy Juknelis, Allstate Insurance Company
    Speakers:
    Amy Juknelis, Property Product Director, Allstate Insurance Company
    Eric O'Neill, The Georgetown Group

GS-2: California Insurance Market — Current Events

No presentation available for download

This closing general session will feature a panel of experts who will address various topics surrounding the current state of the insurance market in the state of California. Our panel will cover issues with Workers Compensation and various Property related natural hazard issues, and will feature a lively Q&A session.

    Moderator:
    Howard Kunst, Chief Actuary, CoreLogic
    Speakers:
    Howard Kunst, Chief Actuary, CoreLogic
    Alex Swedlow, President, California Workers' Compensation Institute
    Shawna Ackerman, Chief Actuary, California Earthquake Authority
    Howard Botts, Chief Scientist, CoreLogic

ICAS: iCAS Community of Practice Event

No presentation available for download

The CAS Institute (iCAS) is offering its first Predictive Analytics Community of Practice event, to be held Monday, March 27th in conjunction with the Casualty Actuarial Society's Ratemaking and Product Management (RPM) Seminar in San Diego. The full-day event, scheduled for 9:00 a.m. to 5:00 p.m., is designed for advanced practitioners working in the area of Predictive Analytics/Data Science, and will include panels, presentations, and roundtable discussions of advanced topics in predictive analytics both within and outside of the insurance fields. Attendance at this event is separate from the RPM Seminar and will require a separate registration fee of $150. (In addition, attendees not attending RPM may attend the RPM opening reception for an additional $35.) Registration at the RPM Seminar is not a prerequisite of attendance.

The content of the inaugural Predictive Analytics Community of Practice day will include:

  • An overview of the new Certified Specialist in Predictive Analytics (CSPA) credential, including its exam process and continuing education requirements.
  • Presentations/workshops on specific topics (within and outside of the insurance field)
  • Roundtables
  • Networking opportunities
  • Master Classes
Topics currently being considered for the program include:
  • Experimental Design
  • Various Modeling Techniques
  • Measuring/Communicating Model Performance
  • Deploying Models and Designing for Implementation
  • Ethics of Predictive Modeling
    Speaker:
    Amy Brener, Director, The CAS Institute

INTNL-1: Internet of Things for International P&C Business

No presentation available for download

In the last few years, we are seeing more and more digital disruption to the global insurance industry. Technology often disrupts mature industries and profoundly changes the business models for those who choose to evolve.

In this session, we will briefly discuss lessons from other industries on how disruptive technologies changes the nature of competition and business models, provide an overview of the three core digital technologies (Internet of Things, blockchain and machine learning) and how these technologies will shake the insurance industry in an unprecedented fashion.

Actual examples will be shown to explain their application in customer data aggregation (entity resolution), product development and product pricing. Furthermore, we will discuss how actuaries can reinvent themselves to play a key role in the innovation process.

    Moderator:
    Lijuan Zhang, Global Manager of Pricing & Portfolio Managment - Individual Personal Insurance, AIG
    Speakers:
    Lijuan Zhang, Global Manager of Pricing & Portfolio Managment - Individual Personal Insurance, AIG
    Yuxiang Lei, Ant Financial
    James Dodge, Practice Leader, Milliman, Inc

INTNL-2: Predictive Analytics in Strategy and Decisions — A Tour Around the Globe

Download Presentation

Predictive analytics can shape key aspects of insurers' business strategies and thus is gaining popularity world-wide. Regional diversity in practice, market conditions and regulation is influencing the way analytics is being implemented around the globe. The availability of data, analytical sophistication and the maturity level of customer-centric views can also influence many business problems. These problems can be addressed by predictive analytics, and the efficiency and precision of actuarial decisions. We can learn from the global differences as well as from the commonalities.

This session will discuss various analytical challenges around pricing, underwriting, retention management, customer life time value, etc. and provide real life examples acquired through numerous projects in over 20 countries around the globe.

    Speaker:
    Reuven Shnaps, Chief Analytics Officer, Earnix Ltd.

MAI-1: Application Of Text Mining In Claims Analytics: A Case Study

Download Presentation

This presentation will discuss applications of text mining in predictive modeling. Text mining can be a valuable tool to add insights to data based on free text entry and unstructured information. When text data is considered, analyses like marketing and consumer sentiment, claims analytics, and even pricing can be enhanced.

We will focus on a case study in claims triaging for workers compensation and personal auto lines. Traditional claims triaging requires experienced adjusters to predict which claims require the most attention to minimize losses. To facilitate this process, senior adjusters can manually review claim notes and descriptions. By using modern text mining techniques on claim notes, however, insurers can better triage and see the big picture of their claims.

Text mining is a set of statistical and machine learning tools in the field of natural language processing. These methods examine a collection of documents and systematically identify important words and patterns. Topic modeling, a newer method in text mining, can also be used to predict which claim types are represented in a given claim. By understanding claim types, this advanced analysis can predict, e.g., whether an apparent "fender-bender" is more like a typical single-payment whiplash claim or more like a multi-payment claim with possible nerve damage.

The presentation will focus on applications with intuitive and visual results, with technical info reviewed at a high-level.

    Moderator:
    Ben Williams, Senior Consultant, Willis Towers Watson
    Speakers:
    William Frierson, Consultant, Willis Towers Watson
    Benjamin Williams, Senior Consultant, Willis Towers Watson

MAI-2: Implementing a Predictive Model: Challenges and Considerations for Success

No presentation available for download

Most of the current focus in data science and analytics is on techniques around data extraction and analysis. And while this focus allows for greater depth of insight into companies' customers, internal practices, and strategies, the immediate output of the data scientist's work – no matter how valuable – does not initially translate to bottom line dollars or other measureable impact. The difference between that initial insight, and the ultimate impact it might have, is the success or failure of its implementation. In this way, implementation is an equally important partner to data and technique in ensuring successful analytics impact.

What have your experiences been with IT, claims, underwriters and actuaries when trying to build and deploy a model? This discussion look past the statistics and will highlight ways to ensure successful implementation across four important factors: data, technology, people, and project management.

    Moderator:
    Kate Jordan, Data Science Senior Manager/AVP, Zurich
    Speakers:
    Kate Jordan, Data Science Senior Manager, AVP, Zurich
    Christopher Zittnan, Associate Data Scientist, Zurich North America

MAI-3: Modeling and Analytics in a UBI Setting

Download Presentation

This session will discuss considerations related to data handling, variable selection, predictive modeling, performance measurement, and program implementation in usage-based auto insurance (UBI). The session will include a carrier perspective as well as content from the UBI chapter of the upcoming textbook Predictive Modeling Applications in Actuarial Science (Volume 2).

    Moderator:
    Jim Weiss, Director - Analytic Solutions, ISO
    Speakers:
    Jim Weiss, Director, Analytic Solutions, ISO
    Gregory Hayward, Asst. Vice President and Actuary, State Farm Insurance Companies
    Udi Makov, Director - Actuarial Research Center, University of Haifa

MAI-4: Point Estimation Models vs. Ranking Models

No presentation available for download

Point estimation and ranking modeling are two types of predictive modeling approaches used in many industries. In P&C insurance, class plan rating, territory rating, and vehicle symbol rating are typical areas for point estimation, while underwriting automation, claim fraud detection, credit scoring and Telematics scoring are typical areas for use of ranking models.

The two types of modeling approaches are fundamentally different in many ways. In this presentation, we will discuss the major differences of point estimation and ranking modeling in the following areas:

  • Model design—Business considerations and technical considerations
  • Predictive variable creation and predictive variable structure
  • Model development and model validation
  • Business implementation and IT implementation
We will use class plan development and underwriting modeling as examples to demonstrate the differences in details.

In this presentation we will also list and describe many interesting applications of the two types of modeling approaches in life insurance, government affairs, and other industries.

    Moderator:
    Gary Wang, Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Speakers:
    Gary Wang, Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Jun Yan, Specialist Leader, Deloitte Consulting, LLP

MAI-5: Enhancing Pricing Precision for Today's Market — The Path to Customer Centricity

No presentation available for download

In response to new market realities, a growing number of North American insurance companies have recognized the need to establish tighter and more engaging relationships with their customers, and are looking into doing so with improved use of analytics.

In the modern age of insurance, financial institutions collect large amounts of customer data. Utilizing a variety of different channels, insurance companies have more information than ever before. However, to improve customer experience, this information needs to be used intelligently. The implementation of customer centric processes and technology does not happen overnight. In the North American insurance industry, a successful implementation necessitates a robust process and technological solution that can cope with a number of specific challenges. These include effective ways of dealing with "Big Data", lack of in-house analytical sophistication, limited time-to-market capabilities, and ability to measure the impact of pricing decisions. This session will review these common hurdles and propose effective solutions to address them.

This session will review common hurdles to adopting this advanced analytics techniques and propose effective solutions to address some of the challenges along the path to Customer Centricity."

    Moderator:
    Reuven Shnaps, Chief Analytics Officer, Earnix Ltd
    Speakers:
    Reuven Shnaps, Chief Analytics Officer, Earnix Ltd.
    Martin Ellingsworth, President, Salt Creek Analytics

PL-1: Concierge Claim Service: The Future of Claims with IoT and Telematics

Download Presentation

As we all know, claims are costly and have a big impact on customer satisfaction, not to mention the insurance company's bottom line. According to InsuranceQuotes.com, even filing one auto insurance claim can cause annual premiums to spike on average 44 percent nationally. Additionally, private passenger auto collision loss ratios have risen to 78.3 percent in 2015. From a customer satisfaction perspective, the dissatisfaction stems from the length of time it takes to be notified of how much the insurer will pay and when the insured actually receives payment. As it relates to property, the impacted customer satisfaction perspective has declined due to the total settlement and service interactions.

IoT, including Telematics, data is changing this archetype by offering holistic claim services. With data from the automakers, alarm companies, and sensor providers, insurers are able to:

  • Offer proactive services to avoid claims
  • Expedite the claim process by getting ‘black box' data and prefilling the claim system in order to leverage their preferred partners for tow dispatch, body shop, and car rental
  • Understand what is happening in the home and reduce loss by mitigating the claim faster, through water sensors, smoke detectors and door sensors
  • Identify fraud
  • Reduce claim cycle time
Be sure to attend to learn how this concierge approach can assist you in improving your personal lines claims efficiency and satisfaction by leveraging IoT and Telematics data.
    Moderator:
    Isaac Wash
    Speakers:
    Jim Weiss, Director, Analytic Solutions, ISO
    Adam Waldron, CIO, Farm Bureau Insurance of Idaho
    Dawn Mortimer, AVP IoT/Telematics Claims Product Development, Verisk Insurance Solutions
    Daniel Sterling, Founder & CEO, Water Hero, Inc

PL-2: Highway Loss Data Institute — Current Issues in Vehicle Safety

No presentation available for download

This session will provide a overview and discussion of current issues in vehicle safety.

    Speaker:
    Kim Hazelbaker, Senior Vice President, Highway Loss Data Institute/Insurance Institute for Highway Safety

PL-3: The Evolution of Classification Rating

Download Presentation 1
Download Presentation 2

Insurance pricing continues to evolve — becoming more sophisticated and predictive. This session will discuss how Personal Lines Auto class plans have evolved and become more granular over time, as techniques and computing power have improved. This session will also present an approach, using a specific case study, for evaluating a modern rating plan using the CAS Statement of Principles on P&C Ratemaking and the Actuarial Standards of Practice. Additionally, we will explore how Usage Based Insurance mechanisms will transform how individual behavior impacts pricing.

    Moderator:
    Claudine Modlin, Willis Towers Watson
    Speakers:
    Claudine Modlin, Willis Towers Watson
    Jeffrey Kucera, Consultant and Actuary, e2Value, Inc.
    Irene Bass, Consulting Actuary, Bass & Khury, Inc.
    Katie DeGraaf, Senior Consultant, Willis Towers Watson

PL-4: Increase Precision in Auto Territory Rating

No presentation available for download

Territorial rating is one of the key elements in auto insurance ratemaking. A territory is defined as a cohort of zip codes or adjacent geographic units with similar loss experience. Auto insurers analyze historical loss experience by garaging location to calculate territorial relativities. Often times, insurers are not allowed to use the indicated relativities due to regulatory constraints governing a territorial plan. This study examines the accident information, and related claim frequency, severity and loss cost by loss location as well as garaging location to calculate a score that can potentially be used in conjunction with insurer's existing territorial plan to improve rate adequacy for individual territories.

    Moderator:
    Hicham Elhassani, Director, LexisNexis Risk Solutions
    Speakers:
    Hicham Elhassani, Vice President of Analytics, LexisNexis Risk Solutions
    Junyi Tang, Statistical Modeler, LexisNexis Risk Solutions
    Prince Kohli, LexisNexis Risk Solutions

PL-5: IoT's Impact on the Distribution, Rating and Underwriting of Personal Auto

No presentation available for download

Until recently, insurers have largely determined car insurance premiums based on characteristics that are proxies for actual driving behaviors. For example, the number of vehicles on the policy and territory are proxies for how much and where the vehicle is driven, respectively. Using actual data that answers when, where, how and how much a vehicle is driven is a much better way to calculate premiums.

While telematics data should play a dominant role in rating algorithms, the data is typically only available after the initial UBI policy has been underwritten and the insured installs the required OBDII sensor or app. While insurers may adjust their traditional rating plans to eliminate obvious overlaps, insurers are still relying heavily on traditional factors to calculate a provisional premium that is subsequently adjusted pending a telematics-based driving score. Auto makers (OEMs), telecommunication companies, mobile handset providers and location-based app providers, etc. (collectively called "data suppliers") either have or will have this data for their customers. Many of these data suppliers are actively pursuing options of how to best monetize existing data through insurance applications. As these services become available, we expect to see game-changing revisions to how insurers price auto insurance.

This session will focus on the how these data suppliers could fundamentally change the way insurance policies are sold, underwritten and rated. The presenters will highlight some of the benefits as well as the challenges for auto insurers.

    Moderator:
    Geoffrey Werner, Global Telematics Leader, Willis Towers Watson
    Speakers:
    Geoffrey Werner, Global Telematics Leader, Willis Towers Watson
    Steven Bishop, Co-Founder - Head of Product, Posit Design, Inc.

PL-6: Vehicle History: Insurance Scoring for Your Car

Download Presentation

To evaluate the risk associated with personal auto coverage, insurers have traditionally primarily used information about the driver, such as age, gender, marital status and location; the intended use of the vehicle, such as business or pleasure; and information about the vehicle when new, such as original cost new. Insurers then added detail to driver information using sophisticated credit scoring and demographic models. They added detail to vehicle use information with telematics and usage-based insurance pricing. Now, insurers have begun to add detail about the vehicle itself using vehicle history.

This session will discuss how carriers use the specific vehicle history to more accurately price and underwrite risks. We will discuss obvious data elements, such as salvage title brands, verified average annual mileage and severe damage. We will also discuss data that may not be as obvious, but has proven predictive of loss in the past. Finally, we will discuss using vehicle history as an entry point for UBI programs. "

    Moderator:
    Don Hendriks, CARFAX Banking & Insurance Group
    Speakers:
    Don Hendriks, Actuary, CARFAX Banking & Insurance Group
    Michael Chen, Consulting Actuary, Pinnacle Actuarial Resources, Inc.

PM-BG-1: Comparing Machine Learning and Conventional Statistical Techniques In Claims Models

Download Presentation

Machine learning methods are becoming popular in insurance modeling applications. In the session, the panelists will discuss a few machine learning methods (gradient boosting, random forests, neural network, LASSO, Elastic Net, etc.) and compare them with conventional regression methods (GLM, generalized mixed models, etc.) in the context of claims triage models. A case study will illustrate the pros and cons of those techniques.

    Moderator:
    Cheng-Sheng Peter Wu, Deloitte Consulting, LLP
    Speakers:
    Cheng-Sheng Peter Wu, Managing Director, Deloitte Consulting LLP
    Joshua Brady, Actuary I, The Cincinnati Insurance Companies
    Luyang Fu, Vice President - Department Head of Predcitive Analytics, The Cincinnati Insurance Company
    Douglas Noe, Predictive Modeler, The Cincinnati Insurance Companies

PM-BG-2: Ensembles and Combining Models

Download Presentation

Ensembles are powerful analytical methods used commonly in the wider Predictive Analytics community outside of Insurance. We'll describe the rationale and explain the effectiveness of Ensembles in general, as well as the basic approaches of bagging and boosting Ensembles of Trees. Advantages of Ensembles on insurance data will be shown and the issues surrounding complex models discussed. Finally, strategies for combining linear regression and ensemble models will be explored.

    Moderator:
    Doug Noe, Cincinnati Insurance
    Speakers:
    Christopher Cooksey, Head Actuary, Data & Analytics, Guidewire Software
    Douglas Noe, Predictive Modeler, The Cincinnati Insurance Companies

PM-BG-3: Overview and Practical Application Machine Learning Methods in Pricing – Part 1

No presentation available for download

The term "machine learning" covers a range of methods that can be powerful, with very practical benefits, in pricing and other insurance applications. Such methods can aid in further improving GLM results or more broadly bring valuable insights to complex problems. There can also be a number of practical challenges in using these methods effectively. This is the first of two sessions reviewing a range of commonly used methods and illustrating different ways they are being applied in insurance. These sessions will focus on the high-level mechanics of each method and the benefits/challenges of their application – as opposed to the underlying technical details. Part 1 will focus on approaches such as penalized regression and other approaches more closely related to GLMs. Part 2 will focus on classification-based approaches, including trees, random forests, and GBMs. Each part can be attended without the other.

    Moderator:
    Claudine Modlin, Willis Towers Watson
    Speakers:
    Duncan Anderson, Managing Director, Willis Towers Watson
    Claudine Modlin, Willis Towers Watson
    Graham Wright, Senior Consultant, Willis Towers Watson

PM-BG-4: Overview and Practical Application Machine Learning Methods in Pricing – Part 2

No presentation available for download

The term "machine learning" covers a range of methods that can be powerful, with very practical benefits, in pricing and other insurance applications. Such methods can aid in further improving GLM results or more broadly bring valuable insights to complex problems. There can also be a number of practical challenges in using these methods effectively. This is the second of two sessions reviewing a range of commonly used methods and illustrating different ways they are being applied in insurance. These sessions will focus on the high-level mechanics of each method and the benefits/challenges of their application – as opposed to the underlying technical details. Part 1 will focus on approaches such as penalized regression and other approaches more closely related to GLMs. Part 2 (this session) will focus on classification-based approaches, including trees, random forests, and GBMs. Each part can be attended without the other.

    Moderator:
    Claudine Modlin, Willis Towers Watson
    Speakers:
    Duncan Anderson, Managing Director, Willis Towers Watson
    Claudine Modlin, Willis Towers Watson
    Graham Wright, Senior Consultant, Willis Towers Watson

PM-BG-5: 2017 NA Survey Results — Machine Learning and Advanced Analytics Practices

No presentation available for download

We live in a world surrounded by analytics. It is everywhere. Sports teams use it to get an edge on the competition, Netflix uses it to predict which shows you are most likely to like and Amazon uses it to introduce you to additional products you didn't even know you wanted. The insurance world is no different. Machine learning and advanced analytics techniques are being used all across the industry for different parts of the pricing process. In this session we will review the interesting findings of a survey conducted around the extent of usage of machine learning and predictive analytics practices among insurance pricing practitioners. Besides learning about the current status of analytics usage, we learned what future insurers are seeing for analytics in the service of pricing. This session will also include live polling to dig deeper into some responses.

    Moderator:
    Dion Oryzak, Insurance Solutions
    Speakers:
    Drew Lawyer, Sr. Professional Services Consultant, Earnix
    Dion Oryzak, Insurance Solutions Olivier Tessier, Professional Services Consultant, Earnix

PMGMT-1: Auto and Home Residual Markets Today: Size, Function and Challenges

Download Presentation 1
Download Presentation 2

The personal lines (auto/home) residual markets look very different today than how they have looked in the past. In private passenger auto, the market is a tiny fraction of what it was in the 1990s, and per policy fixed costs to service this market have increased significantly. In homeowners, coastal residual markets have demonstrated elasticity to respond to storm cycles (or lack thereof), with related changes in industry assessment potential. This session will provide an overview of the mechanisms that currently operate to service the US personal lines residual markets, and provide insight into how reforms may benefit the industry and the consumer.

    Moderator:
    James Rowland, Allstate Insurance Company
    Speakers:
    James Rowland, Senior Actuary and Residual Markets Director, Allstate Insurance Company
    Gina Schwitzgebel, General Manager, North Carolina Joint Underwriting Association, North Carolina Insurance Underwriting Association

PMGMT-2: Competitive Analysis: Know the Data, Know the Market

Download Presentation 1
Download Presentation 2

Competitor data is a powerful ingredient of rating algorithm development, predictive modeling, and measurement of product performance in the marketplace.

While the use of this data is widespread, the benefit received by insurers depends on the extent and manner in which it is utilized. To utilize the data to its full extent, actuaries should be familiar with the types of data available, the assumptions that underlie them, and strategies to incorporate competitive intelligence into decision-making.

Competitive data is available from different sources, including batch rating companies and agency software companies. In this session, representatives from each of these provider types, plus consultants who specialize in competitive analysis, will illustrate the spectrum of competitive offerings in the marketplace and how each of them can be used. This will include specific ways to evaluate key metrics such as conversion, retention, market penetration, and segmentation.

Session attendees will become apprised of the lay of the land for competitor data. They will leave with an in-depth understanding of what is available, and specific steps that can be taken to utilize it fully.

    Moderator:
    Nancy Watkins, Milliman, Inc.
    Speakers:
    Nancy Watkins, Principal, Milliman, Inc.
    Cody Webb, Actuary, Milliman
    Mike Weitermann, Director of Product Management, LexisNexis Risk Solutions
    Joann MacCaul, Sr Product Manager, Vertafore

PMGMT-3: Multi-Product Optimization: Challenges and Opportunities

No presentation available for download

When trying to understand the customer decision making process it is easiest for us to break the customer decisions into independent, discrete choices: "Will I renew my auto policy?", "Will I add my motorcycle this year?", "Will I cancel my homeowners policy before renewal?". These decisions are not made in a vacuum, even though that is the easiest way for us to model them. The real decision making process is a highly complex one which takes information across multiple products into account.

In this session we will dive into the complexity of multi-product optimization. We will begin by discussing the advantages of a holistic view for customer decision modeling and then analyze the barriers to adopting a multi-product optimization strategy. Attendees will leave with a practical roadmap of steps they can follow in order pave the way for multi-term optimization.

    Moderator:
    Drew Lawyer, Earnix
    Speakers:
    Drew Lawyer, Sr. Professional Services Consultant, Earnix
    Bruno Tremblay, Senior Actuarial R&D Analyst, La Capitale

PMGMT-4: Perspectives on Actuarial vs. Product Management Roles

Download Presentation

Have you wondered if a product management role is for you? In this session we will hear from panelists who have held both actuarial and product management roles in their careers. The panelists will discuss topics such as contrasting experiences as a product manager versus an actuary, what it takes to be successful in a product management role, and how current marketplace developments are impacting product management.

    Moderator:
    Kelly Cusick, Senior Manager, Deloitte Consulting, LLP
    Speakers:
    Amy Juknelis, Property Product Director, Allstate Insurance Company
    Kelly Cusick, Managing Director, Deloitte Consulting, LLP
    Don Hendriks, Actuary, CARFAX Banking & Insurance Group
    Scott Drab, AVP - Product Leader, Small Commercial & Farm, Grange Mutual Casualty Group

PMGMT-5: Residential Flood Insurance in Canada and Learnings for the US

Download Presentation 1
Download Presentation 2
Download Presentation 3
Download Presentation 4

In the last two years, at least fifteen insurers in Canada have introduced new products to cover overland water. This cause of loss was previously excluded in policy wordings and losses would have been paid by government disaster relief funds. However, after a $2B fluvial loss in Calgary and a $1B pluvial loss in Toronto within a few weeks of each other in 2013, an appetite was created for the private market to explore options. This session will explore the current situation in North America, focusing differences in risks and modeling between countries, challenges in product development, implementation and management, market responses to date, and anticipated future developments in both the modeling and product space. This session will be of interest to US practitioners as the collective experiences of panel members will be relevant to the prospect of further privatization of the US flood insurance market.

    Moderator:
    Brant Wipperman, Peace Hills Insurance
    Speakers:
    Deborah Upton, Director of Actuarial Services, Gore Mutual Insurance Company
    Brant Wipperman, Actuary, Peace Hills Insurance
    Frederick Guillot, Sr Manager - Research & Innovation, The Co-operators General Insurance Company
    Adam Podlaha

PM-LM-1: GLM - I

Download Presentation

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 in addition to mathematical calculations. Illustrations will be presented using actual insurance data."

    Speaker:
    Ernesto Schirmacher, Senior Managing Actuary, Liberty Mutual Insurance

PM-LM-2: GLM - II

Download Presentation 1
Download Presentation 2

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 also include a discussion on diagnostics that help test the selections made.

    Moderator:
    Ernesto Schirmacher, Liberty Mutual Insurance
    Speakers:
    Ernesto Schirmacher, Senior Managing Actuary, Liberty Mutual Insurance
    Paul Bailey, Consultant, Willis Towers Watson

PM-LM-3: GLM - III — The Matrix Reloaded

No presentation available for download

This session will consider new techniques and refinements to the basic GLM which can add material value to the modeling process. It will specifically consider amendments which address some of the purported failings of GLMs in comparison to emerging methods such as machine learning techniques.

The session will include a discussion of:

  • An innovative approach to detecting subtle and higher dimensional interactions in an efficient way, potentially eliminating the need to consider alternative, harder-to-implement model forms such as nonlinear models.
  • The role of such automated methods in comparison with a more manual construction of composite explanatory variables.
  • Ways to mitigate the risk of over-parameterization through the use of modifications which incorporate elements of credibility within the GLM framework.
  • Simple practical modeling steps that can be used to remove distortions created by combining models across claim types.
  • Innovative ways of modeling bodily injury claims and other miscellaneous refinements.
    Speaker:
    Brent Petzoldt, VP, Head of Pricing, JLT Re

PM-LM-4: And the Winner Is: How to Pick a Better Model

Download Presentation 1
Download Presentation 2

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 is usually a major investment. We should make sure our models are performing well to get the best bang for the buck.

    Moderator:
    Hoi Leung, Director of Predictive Analytics, AIG
    Speakers:
    Dan Tevet, Director II, Data Science, Liberty Mutual Insurance
    Hoi Leung, Director of Predictive Analytics, AIG
    Hernan Medina, Senior Principal Data Scientist, ISO

PM-LM-5: Nonparametric GLMs

Download Presentation

GLMs provide a powerful modeling framework but often their rigid structure does not allow for an optimal model. Learn how to build basic nonparametric models with a limited number of variables and how to apply nonparametric techniques to improve existing GLMs with an unlimited number of variables.

    Speaker:
    Ryan Morrison, CEO, True Mileage, Inc.

PRO-1: Discussion of ASOP Exposure Draft: Estimating Future Costs for Prospective Property/Casualty Risk Transfer and Risk Funding

Download Presentation

The Actuarial Standards Board recently released for comment an exposure draft Actuarial Standard of Practice (ASOP) entitled "Estimating Future Costs for Prospective Property/Casualty Risk Transfer and Risk Funding". This exposure draft follows exposure and comment on two previous exposure drafts related to Property/Casualty Ratemaking.

With this exposure draft, the scope as well as the title has been revised to clarify that the draft ASOP is limited to estimating the future costs for prospective property/casualty risk transfer and does not include the preparation of rate filings and issues related to the interactions between ratemaking, pricing decisions and rate regulation.

The panelists will cover the key components of the current exposure draft. The areas covered in the draft ASOP include all of the items currently listed in the Considerations Section of the Statement of Principles Regarding Property-Casualty Insurance Ratemaking adopted by the Casualty Actuarial Society in 1988.

Attendees will also be encouraged to provide their comments and suggestions directly to the ASB in their formal process for consideration.

    Moderator:
    Christopher Carlson, Ohio Bureau of Workers' Compensation
    Speakers:
    Christopher Carlson, Chief Actuarial Officer, Ohio Bureau of Workers' Compensation
    Patrick Woods, Retired

PRO-2: Lights! Camera! Professionalism!

No presentation available for download

Come enjoy the acting of some fine fellow actuaries who will take on several skits involving professional dilemmas. The skits are new for 2017, 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.

    Moderator:
    Michael Chen, Pinnacle Actuarial Resources, Inc.
    Speakers:
    Michael Chen, Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Jennifer Vincent, Director of Pricing and Product Management, Government Employees Insurance Company
    Brandon Shain, Associate Actuary, GAINSCO Auto Insurance

PRO-3: Rogue Actuary: A Professionalism and Predictive Modeling Story

No presentation available for download

During the past decade, predictive modeling has increasingly become part of many actuaries' job descriptions. Whether building predictive models, inserting them as inputs to the pricing decision-making and implementation process with business partners, or supporting them in rate filings, actuaries are often asked for their opinions on issues that relate to the ethics of the profession. This session has been given at several previous RPM seminars and the interactive format will remain the same, although the scenarios have been refreshed. Scenarios that touch on common issues around predictive modeling will be presented, including how those issues relate to the Code of Conduct, Statement of Principles, and Standard of Practice. Audience participation is highly encouraged. May the Professionalism be with you.

    Moderator:
    Brent Petzoldt, JLT Re
    Speakers:
    Brent Petzoldt, VP, Head of Pricing, JLT Re
    Nathan Hubbell, 2VP, Analytics & Research, Travelers

PRO-4: Who Wants to Be an Actuary?

No presentation available for download

Come refresh your knowledge of actuarial professionalism in this interactive session! This trivia game will cover a number of topics including a review of the code of conduct and ASOPs, helping you determine what you know and what you might want to review. Who said professionalism can't be fun? This session may provide attendees with Professionalism Continuing Education credits.

    Moderator:
    Kendall Williams, COUNTRY Financial
    Speakers:
    Kendall Williams, Manager, Property / Casualty Actuary , COUNTRY Financial
    Peter Royek, Senior Vice President & Actuary, The Toa Reinsurance Company of America

REG-1: Navigating the Regulatory Environment Around Usage-based Insurance

Download Presentation

Usage based auto insurance has had a mixed reception among US insurance regulators. While most regulators would support UBI for its potential to promote greater fairness in rating, some would object due to the apparent invasion of driver privacy, among other things. Hear from an actuary and a product manager from Verisk with years of experience filing UBI products.

    Moderator:
    Thomas G. Hess, Assistant Actuary, Ohio DOI
    Speakers:
    Thomas Hess, Assistant Actuary, Ohio Department of Insurance
    Isaac Wash, Product Manager, Telematics, Verisk Analytics
    Jared Smollik, Director, ISO Solutions

REG-2: Perspectives on Rate Filing Support for Predictive Models

Download Presentation 1
Download Presentation 2
Download Presentation 3

While the use of predictive analytics to develop rate classifications has become a widely accepted technique in the insurance industry, they can create additional challenges during the filing process due to their apparent black box nature. While some insurance departments may only require indicated and proposed rating factors, others may require substantially more support including such items as confidence intervals, lift charts or comparisons to other insurance companies.

This session will provide different points of view on filing support for predictive models, including perspectives from those submitting rate filings (insurance company or consultant) and those reviewing the rate filings (insurance department or independent third party reviewer). In this session, we will discuss modeling topics as they relate to filing support such as volatile results and thin data, extrapolating and smoothing indicated relativities, and the use of actuarial judgment. We will provide perspectives on how to best submit rate filings that rely on predictive modeling techniques beyond GLMs.

    Moderator:
    Eric Krafcheck, Milliman
    Speakers:
    Eric Krafcheck, Consulting Actuary, Milliman
    Paul Anderson, Principal & Consulting Actuary, Milliman
    Ryan Purdy, Consulting Actuary, Merlinos & Associates
    Edward Cimini, Senior Casualty Actuary, California Department of Insurance

REG-3: Price Optimization: Regulatory Overview and Permitted Practices

No presentation available for download

This session will provide an overview of the price optimization debate, including how price optimization is defined, the historical development of price optimization in insurance, NAIC and state activity, and other ongoing developments. The presenters will also discuss the development of price optimization ratemaking practices, how the practice has evolved, and some fundamentals of how price optimization works from a non-technical perspective, as well as regulators' reactions to this modern practice. Understand the current state of the price optimization debate. Know what price optimization is (and is not). Understand the mechanics of price optimization.

    Moderator:
    Ryan Purdy, Merlinos & Associates
    Speakers:
    Ryan Purdy, Consulting Actuary, Merlinos & Associates
    Fred Karlinsky, Shareholder, Greenberg Traurig

REG-4: Rate and Form Regulation — The Latest from the NAIC

Download Presentation 1
Download Presentation 2

State insurance regulators at the NAIC are discussing big data and other consumer data, generalized linear and other models used in insurers' rate filings, rate classification issues (capping — what is price optimization and what is not — and causation vs. correlation), private flood insurance, workers' compensation large deductibles, and other regulation of property/casualty insurance products. Hear about the latest activities and likely impact on actuaries and product managers in ratemaking and product development.

    Moderator:
    Kris DeFrain, NAIC
    Speakers:
    Kris DeFrain, Director - Research and Actuarial , National Association of Insurance Commissioners
    Charles Angell, Deputy Commissioner & Chief Actuary, Alabama Department of Insurance
    Nicole Elliott, Actuary, Texas Department of Insurance
    David Dahl, Casualty Actuary, Oregon Division of Financial Regulation

REG-5: What Makes a Good California Filing?

Download Presentation

Learn how to improve the quality of your California rate & class plan, form and rule filings. This session will also provide you with some common stumbling blocks that delay the approval of your rate filing.

    Moderator:
    Shawna Ackerman , FCAS, MAAA Chief Actuary California Earthquake Authority
    Speakers:
    Lynne Wehmueller, Senior Casualty Actuary, California Department of Insurance
    Shawna Ackerman, Chief Actuary, California Earthquake Authority

WC-HC-1: Workers Compensation—State of the Market

Download Presentation 1
Download Presentation 2
Download Presentation 3

An overview of the current state of the workers compensation line will be presented, including a review of financial results, recent trends, and a discussion of where the line might be headed.

    Moderator:
    Jay Rosen, National Council on Compensation Insurance, Inc.
    Speakers:
    Jay Rosen, Director and Senior Actuary, National Council on Compensation Insurance, Inc.
    Nancy Treitel-Moore, Director, Liberty Mutual

WC-HC-2: Workers Compensation—Selected State Issues

Download Presentation 1
Download Presentation 2

The panel will present a summary of the key issues and challenges facing the workers compensation system in the states of California and Florida.

In Florida, major philosophical shifts in the operation of the workers compensation system have recently been experienced as a result of the Castellanos and Westphal decisions, related to attorney fees and temporary total maximum claims duration, respectively. NCCI will present a summary of the associated legislative issues and related cost-impact analyses.

Despite several attempts to reform the system over the last several years, California continues to be a very high cost state with respect to workers compensation—with a very high frequency of permanent disability claims, a long average claims duration, and exceptionally high benefit delivery costs. WCIRB of California will present a summary of the key factors driving California cost levels as well as a prognosis for future changes in those drivers.

    Moderator:
    John Deacon, NCCI
    Speakers:
    David Bellusci, EVP & Chief Actuary, WCIRB of California
    John Deacon, Director & Actuary, NCCI

WC-HC-3: Hospital Professional Liability—How Do We Price a Moving Target?

Download Presentation

Over the past several years, the medical community has consolidated from private practices into larger groups, with many physicians seeking employment at hospitals. As a result, Hospital Professional Liability business has taken on an increasing share of Medical Professional Liability business. Hospitals are also going through many changes, including major changes to healthcare delivery, shifts in the judicial environment, and a rapidly growing number of mid-level providers. The ability for actuaries to provide accurate rates is becoming more challenging. In this session, we will summarize the sources of information that actuaries can reference, and identify shifts that are likely to impact professional liability costs for hospitals.

    Moderator:
    Joshua Youdovin, New York Compensation Insurance Rating Board
    Speakers:
    Joshua Youdovin, Assistant Vice President, New York Compensation Insurance Rating Board
    Charles Mitchell, Actuary, Mitchell Consulting LLC
    Timothy Mosler, Senior Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Robert Allen, President, Pro-Praxis Insurance

WC-HC-4: Impact of PPACA on Workers Compensation Insurance

Download Presentation 1
Download Presentation 2

Please join Len Herk and Jerry Frye as they discuss the impact of the Patient Protection and Affordable Care Act (PPACA) on workers compensation insurers and access to care for injured employees.

Len Herk, a Senior Economist at NCCI, will discuss his recently published study "Impacts of the Affordable Care Act on Workers Compensation." In the study, he addresses the frequently asked question, "Has the increase in demand for primary care services by people newly insured under the ACA crowded out access to the same services by workers compensation claimants?"

Jerry Frye, President and Founder of BSG Analytics, will focus on the reaction of the large health care systems to the PPACA which has led to many changes in the way care is provided. These changes have many implications to the workers compensation market, and may help to explain the findings in Len's study.

    Moderator:
    Kevin Donnelly, UnitedHealthcare
    Speakers:
    Kevin Donnelly, Actuarial Consultant, UnitedHealthcare
    Gerald Frye, President, The Benefit Services Group, Inc.
    Leonard Herk, Director & Senior Economist, NCCI

WC-HC-5: Using Predictive Analytics to Decompose Workers Compensation Loss Triangle Anomalies

Download Presentation 1
Download Presentation 2

Loss triangles often produce reserve estimates that are unusual for a particular evaluation. For example, where the previous three years might indicate a 1.25 change in reserves at a particular evaluation, the latest indication is a 1.40 change. Often such an anomaly requires checking with underwriters, claim adjusters, case managers, and other operations specialists to understand the unusual adverse loss experience. By contrast, advances in predictive analytics are allowing for much more granular decompositions of claim experience that permit isolating changes in claim frequency and severity for narrow subgroups of claims or claim characteristics. For example, a Segmentation Analysis might identify an unusually large number of claims for a high-cost segment, an unusually large increase in severity for a moderately-severe segment, or some combination of both. Segmentation analysis can tease-out changing associations between specific claim characteristics (increasing or decreasing opioid utilization, cumulative trauma and attorney involvement) and their associated outcomes.

The panelists will describe a general framework for the predictive analytics and provide a detailed example of a Segmentation Analysis that uses claim characteristics to segment (or to some, cluster) claims into mutually exclusive subgroups, and then analyze frequency and severity changes for these subgroups across different evaluations in the loss triangle. The panelists will also describe information the actuary should consult to determine whether the changes to the subgroups is systemic to the book of business or due to external changes. The external changes may include public policy changes, change in adjudication practices, or changes in market claim trends.

    Moderator:
    Lori Julga, Principal & Consulting Actuary, Milliman
    Speakers:
    Lori Julga, Consulting Actuary, Milliman
    Philip Borba, Senior Consultant, Milliman, Inc
    Alex Swedlow, President, California Workers' Compensation Institute

Workshop 1: Severe Weather

No presentation available for download

This workshop provides educational opportunities to learn both about the science and methods used to build weather models, but also provides useful information on how weather can be used within the business of insurance.

    Moderator:
    Howard Kunst, Chief Actuary, CoreLogic
    Speakers:
    Howard Kunst, Chief Actuary, CoreLogic
    Nancy Watkins, Principal, Milliman, Inc.
    Thomas Jeffery
    Eric Robinson, Senior Scientist - Research and Modeling, AIR Worldwide
    Edward Byrns
    Don Windeler

Workshop 2: Basic Predictive Modeling

No presentation available for download

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 generalized 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.

    Speaker:
    Mark Goldburd, Consulting Actuary, Milliman

Workshop 3: Product Development

Download Presentation 1
Download Presentation 2
Download Presentation 3

This workshop will explore the different stages of product development with hands on exercises for the attendee. Industry leaders will serve as facilitators to review historical processes and to help guide the attendees throughout the day. Attendees will work in teams to develop fictitious products that will be discussed and integrated into the facilitator's lesson plans.

    Speakers:
    Kelly Cusick, Managing Director, Deloitte Consulting, LLP
    Don Hendriks, Actuary, CARFAX Banking & Insurance Group
    Thomas Hess, Assistant Actuary, Ohio Department of Insurance
    Serhat Guven, Director, Willis Towers Watson

Workshop 4: Introduction to R

Download Presentation 1
Download Presentation 2
Download Presentation 3
Download Presentation 4
Download Presentation 5
Download Presentation 6

Are you one of the millions of actuaries around the world who wish they could draw maps showing the progress of hurricanes, fit generalized linear models to predict sporting events, create complex Monte Carlo simulations, or fit loss distributions? Or maybe you're the sort of person who wants to fit a stochastic reserving model and have a computer display stacks of pretty pictures for you. Do you want one point of access for all of your Excel, text, database and web-based data? Are you fascinated by programmers whose first names begin with the letter "R"?

If that's the sort of person you are, this is the workshop for you. And if none of those people is you, maybe all you want is to be able to get R to work for your computer. We can take care of that too.

R is the single most important technological advance for actuaries since the invention of the pocket calculator. Come see what all the fuss is about.

    Moderator:
    Gary Wang, Pinnacle Actuarial Resources, Inc.
    Speakers:
    Gary Wang, Consulting Actuary, Pinnacle Actuarial Resources, Inc.
    Emma Li, Data Scientist, Euclid Analytics
    Scott Sobel, Principal, Oliver Wyman Actuarial Consulting
    Radost Wenman, Consulting Actuary, Pinnacle Actuarial Resources, Inc.

Workshop 5: Capital Allocation and Risk/Reward Decision-Making in an ERM Framework

No presentation available for download

This workshop will provide a historical primer on the subject and address past and current research of the practical ways in reflecting the cost of capital for ratemaking and decision-making. This primer will discuss aspects as developed by Merton-Perold, Myers-Read, Mango's asset share model, and the RMK procedures. Also considered will be current research as it relates to how actual capital should perhaps be considered in percentile layers and/or traunches, based on the risk metrics considered. We have come a long way in ratemaking since using premium to surplus ratios of 30 years ago. Let's continue the evolution. A laptop is recommended for participation in this session as we will have hands-on technical sessions where the audience will be charged with an exercise in allocating capital to lines of business considering various methods. Participants will work in groups to make strategic recommendations based on their respective results. Role playing will be involved. Attendees will have access to data in advance.

    Moderator:
    Robert Wolf, StoneTrust Commercial Insurance Company
    Speakers:
    Robert Wolf, Vice President and Chief Actuary, StoneTrust Commercial Insurance Company
    Neil Bodoff, Executive Vice President , Willis Towers Watson

Workshop 6: Advanced Predictive Modeling

Download Presentation 1
Download Presentation 2
Download Presentation 3
Download Presentation 4

Although the Generalized Linear Model (GLM) is a natural foundation for much actuarial work, it is best viewed as a starting point, not the last word on the subject. This day-long, hands-on, R-based workshop will discuss a variety of statistical learning methods that either refine or serve as complements to the GLM framework. Generalized Additive Models [GAM] will be discussed as a means to capture potentially complex nonlinear relationships.

Multilevel/hierarchical models, ridge regression, and lasso regression will be discussed as a way of achieving shrinkage ("credibility weighting") effects within linear models.

Various forms of tree-based modeling (CART, random forests, boosted trees) will be used to exemplify the use of non-parametric, machine learning, and ensemble methods. Time permitting, other machine learning methods such as support vector machines [SVM] and artificial neural networks [ANN] will also be discussed. Core themes such as the bias-variance trade-off and cross-validation will be woven throughout the presentation. The workshop will assume a working knowledge of the R statistical computing environment and GLM modeling.

    Moderator:
    Mark Jones, Director, PricewaterhouseCoopers
    Speakers:
    Mark Jones, Director, PricewaterhouseCoopers
    Kudakwashe Chibanda, Actuarial Manager, PricewaterhouseCoopers
    Jean-Francois Greeff, Senior Associate, PricewaterhouseCoopers
    Prashant De, Data Scientist, Startup

Workshop 7: Data Visualization: GIS for Actuaries

No presentation available for download

This workshop is intended to introduce actuaries to the wonderful world of geographic information science (GIS). GIS can be used to visualize insurance data at a range of scales all the way down to the policy or location level. Additional applications include appending third-party data, enhancing analysis using geographic relationships, and the creation of customized or granular rating territories.

The first part will be a lecture on GIS basics such as data types, geocoding addresses, locating and using third-party data, cartographic representation, and simple geoprocessing workflows.

The second half will be a hands-on tutorial taught in ArcGIS for Desktop. Instructions on software and data installation will be provided to all participants that pre-register.

    Speaker:
    Garrett Bradford, Cartography and GIS Analyst, Milliman, Inc.

Quick Poll

What webinar topic would you like to see most?

Multiple Choice

 

On-Demand Continuing Education Credit

The CAS Roundtable

Posted on 09/21/2017
By Brian Brown

Read More