Economic and Technological Changes Drive Frequency and Severity Growth for Auto Insurers – What can we Expect Moving Forward?
The U.S. automotive insurance market will face numerous challenges in 2018 and beyond. As the auto industry responds to changing vehicle technology, changing notions of personal mobility, and growth of digital technologies, the internet of things (IoT), artificial intelligence (AI), and analytics, the type of insurance product carriers will underwrite and the way claims are resolved is changing. As the industry works to meet the demands of an increasingly digital customer base, they are dealing not only with changing consumer expectations; simultaneously the vehicles being driven by their customers are also becoming ever more complex. As automakers have responded to government regulation on fuel economy, emissions reductions, safety, and other factors, new products and technologies have been developed that have led to a much more technologically sophisticated vehicle fleet.
This session will focus on the key drivers behind growing frequency and severity within the auto insurance sector, and what the trend for the future may look like, as the marketplace responds to the ever-increasing rate of change.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
David Moore
Panelists:
James Lynch, Susanna Gotsch
Overview and Practical Applications of Machine Learning Methods in Pricing - Part 2
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, including some case study results. 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 tree-based methods including random forests and GBMs. Part 2 will cover other popular methods including penalized regression methods and neural networks. Each part can be attended without the other.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
David Moore
Panelists:
Graham Wright
Overview and Practical Applications of Machine Learning Methods in Pricing - Part 1
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, including some case study results. 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 tree-based methods including random forests and GBMs. Part 2 will cover other popular methods including penalized regression methods and neural networks. Each part can be attended without the other.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
David Moore
Panelists:
Graham Wright
Blockchain: Finding Real Opportunities Behind the Hype
Blockchain technology is already significantly impacting the insurance industry’s business models and products. Consumer behavior has changed following new needs and expectations. The nature of risk is evolving incorporating new sources of risk and more risk interconnectedness. New ways of measuring and tracking risk in real time allow for innovative risk fragmentation. New players are exploring different ways of allocating risks and interacting with customers. The acceleration in the #insurtech space significantly increased investments in new technologies. One of those new technologies is Blockchain.
This session will navigate the blockchain hype and explore what a blockchain is and isn’t, identify how blockchains can disrupt the insurance industry, and outline the threats and opportunities that players will have to navigate. It will start with a brief Blockchain 101 and then discuss the implications of the technology in more depth by delving into the latest use cases and existing insurance products based on blockchain technology. The last third of this session will be interactive and will provide food for thought to actively discuss the latest blockchain insurance protocols with the audience.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Magdalena Ramada Sarasola
The Future of UBI: Analytics and Distribution
In this session, we will discuss the landscape for the future of auto telematics in the insurance space. We will emphasize how the industry is moving beyond simple scores and discuss how the pending changes to the distribution of insurance are upon us.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Joseph Griffin
Artificial Intelligence and Advanced Insurance Analytics: Techniques, Technology, and Promise
The explosive growth in data science has generated considerable enthusiasm for data analysis across all industries. Exciting new tools developed in the technology industry are driving change across all industries. It is easier than ever to change the technical backbone of a company or department, but it remains difficult for insurers to understand whether they should be pursuing, monitoring, or simply ignoring some of the newest trends. In this discussion, we will recap the basic concepts in artificial intelligence and take a candid approach to filtering through these innovations. We will also discuss a framework for identifying opportunities within your own organization.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Jason Rodriguez, Rachael McNaughton
Nonparametric GLMs
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.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Blake Berman
Panelists:
Ryan Morrison
Vehicle History: Insurance Scoring for your Car
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.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Joshua Merck
Panelists:
Michael Chen, Donald Hendriks
Recent Trends in Mileage: An Insurance Industry Perspective
Over the last several decades, the number of miles people drive on a daily basis has changed dramatically. At the end of the 20th century, more and more people took on long commutes, pushing average mileage up. Factors like the Great Recession of 2007, ridesharing, and a resurgence of the inner cities have had the opposite effect. Because mileage is a direct reflection of exposure to loss, insurers need to understand how vehicles are used in order to properly rate and underwrite them. This session discusses recent trends in mileage and ways insurers can use mileage to better understand the pricing and underwriting exposures they face.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Gary Vadnais
Panelists:
Matthew Moore, Daniel Hill, David Grove
Bridging The Transparency Gap with Geospatial Intelligence
Rewrite the analytical rules by utilizing real-time geospatial data with time-tested profit strategies. Are actuaries, underwriters, claims adjusters, product managers and marketing reps all working from the same roadmap? Why personal lines insurance is behind the times using data in a more meaningful way.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Gary Vadnais
Panelists:
David Jowell
What Makes a Good Rate Filing?
What makes a good rate filing? It depends on whom you ask. Now is your opportunity to hear from individuals who have extensive experience with the filing process at companies, bureaus, and insurance departments. Here is your chance to find the commonalities and differences in their perspectives.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Joshua Merck, Julie Lederer
Panelists:
Christopher Cooksey, Lawrence Steinert, Thomas Hess
Census Data and Geography in P&C Insurance
The U.S. Census Bureau produces a wealth of data products including demographic and economic data as well as geographic reference and boundary information. This session will provide an introduction into census data (where to get it and how to map it) and then present a variety of case studies focusing on GIS application of census products for P&C Insurance.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Derek Freihaut
Panelists:
Garrett Bradford, David Evans
Insurance Disruption - How to Modernize your Insurance Product and Roll out Changes in Six Months
We will start with success stories of companies modernizing their existing products. We will review how to identify and incorporate modern coverage design, service, and digitization. Then we will discuss how to prepare your filing support to support an efficient regulatory approval across 50 states in the US. If done right, you can launch product changes across all 50 states within 6 months of starting the product evolution process.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Jean-Philippe Boucher
Panelists:
Sheri Scott
Capital Allocation and Risk/Reward Decision-Making
This workshop 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.
A laptop is needed 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.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Workshop
Moderators:
Julie Lederer
Panelists:
Robert Wolf
Analytics Roadmap for Smaller Companies: Investing in the Right Tools and Techniques
The analytic challenges for a $10 billion company are very different from those of a $100 million company. Smaller companies have always found innovative ways to compete with the larger companies through distribution channels, customer relations, and target marketing. One of the new competitive frontiers in the industry is analytics – companies that are able to effectively leverage analytics are seeing a great return on their investment. Unfortunately for smaller companies, larger carriers are at an advantage simply from the availability of resources.
In this session we will discuss what smaller companies (primarily those under $500 million) can do to compete in the analytics arms race. Not all analytics activities provide the same return on investment; here we will outline some of the most cost effective analytics initiatives spanning across product enhancement, tools, and methodology. This session will also address the talent gap that many smaller companies face and the most effective ways to address it.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Derek Freihaut
Panelists:
Marcus Deckert, Drew Lawyer
Price Optimization
As Price Optimization has gained more traction in the insurance industry, there has been a divergence of opinions regarding the legitimacy of its use ranging from acceptance to outright banning of the practice. This session will cover the different perspectives of the conversation including a historical view, a consumer advocacy perspective and the current regulatory environment.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Birny Birnbaum, Serhat Guven, Wanchin Chou
Professionalism and the 2016 Presidential Election Cycle
Great effort has been expended in politics analyzing what went right and wrong in predicting outcomes of recent votes such as the ‘Brexit referendum’ and the 2016 US presidential election. If similar effort had been spent perusing professional guidance such as the Actuarial Standards of Practice (ASOPs) before the votes, could political pollsters have potentially improved their prediction accuracy? And are actuaries subject to the similar risks of prediction error as many pollsters were? At the heart of these questions are issues such as validity and transparency of assumptions, quality of data, and relevance of the past in predicting the future, many of which are addressed in the ASOPs. In this interactive session we analyze political prediction processes, draw insurance analogies, and debate appropriate professional considerations for actuaries as contained in the standards.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Julie Lederer
Panelists:
Jim Weiss, Daniel Moskala
Cluster Analysis in Loss Development
Cluster analysis is a collection of statistical tools designed to group similar data objects. In this session, we will look at these tools applied to grouping of similar loss development patterns.
In ratemaking, loss experience is typically aggregated into development triangles according to the needs of state-by-state rate filings. In loss reserving, losses are typically aggregated based on financial reporting categories. Cluster analysis can help to investigate more optimal ways of grouping the data. This session will discuss some useful ways to visualize the clusters and share some practical successes and challenges in applying clustering on loss development triangles. Topics include “hard” clustering such as k-means and “soft” or “fuzzy” clustering with similarities to traditional credibility theory.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Scott C. Anderson
Panelists:
David Clark, Diana Rangelova
Crime Data with Applications to Ratemaking
A discussion of geography specific crime data, including common sources of raw data, difficulties associated with data consistency across space, and tradeoffs between generalization and high-resolution data. Session will discuss current crime rating algorithms and applications in ratemaking methodologies as well as potential refinements for future uses.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Barbara Murray
Panelists:
Ajay Marathe, Bjorn Markeson
Insurance-Linked Securities(ILS) Market’s Reaction to Losses in 2017
ILS markets were founded to provide property coverages against natural catastrophes. ILS markets have historically provided market leadership and stability around catastrophe events – how has the market responded to losses in 2017? As we look forward to future opportunities, what lies ahead? ILS managers and investors have matured significantly since the founding days and what opportunities are available to take the market to the next level? The nearest answer seems to be specialty lines - ILS funds have demonstrated an appetite for specialty and there’s a clear market opportunity for larger capacity. Join us for a lively discussion of how ILS capital can complement current capacity to help clients achieve target ROEs and investors achieve attractive financial returns.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Scott C. Anderson
Panelists:
Sean McCarty, Tom Johansmeyer
Introduction to Profit and Contingency Loading in Ratemaking
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.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Julie Lederer
Panelists:
Robert Wolf, Ira Robbin
Customer Centric Pricing: Infusing Customer Lifetime-Value into your Pricing and Processes
The idea of customer centricity has been getting a lot of coverage lately; however, most of the content is focused around the strategic importance of customer centricity. One learning from this strategy - not all policyholders are created equal. This can be a controversial concept in many companies, and for some companies, the days of treating all customers equal is ending. Having the right metrics in place is critical for the “customer centric” company of the future. While many companies talk about Lifetime-Value, very few have successfully managed to develop, deploy, and act upon such a highly praised metric.
In this session, we will focus what companies are practically doing to integrate the concepts of customer centricity into their pricing practices. We will cover the evolution from cost based pricing through lifetime-value pricing. This session will help demystify the elusive CLTV metric by exploring the advantages and disadvantages of different calculation methods, and glimpse into how the most successful companies are leveraging these metrics to drive change and improve business results. Attendees will learn new insights into what initiatives they should pursue today to prepare for the future of customer centric pricing
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Drew Lawyer, Reuven Shnaps, Ph.D
Recent Developments and Common Pitfalls in Property and Casualty Rate Filings
Regulators will discuss common pitfalls in property and casualty rate filings and in insurer supporting information for predictive models. Regulators will also describe the recent evolution of credit-based insurance scoring and use of consumer behavioral characteristics in predictive models, commenting on both helpful aspects of these recent developments and aspects that raise significant concerns.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Featured Speaker
Moderators:
Julie Lederer
Panelists:
Kris DeFrain, Gennady Stolyarov, Wanchin Chou, Richard Piazza, Daniel Davis
The Three P's and The J - Professionalism, Pricing, Predictive Modeling, and...
Predictive modeling has increasingly become a 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. We’ll look to the future of predictive modeling and pricing as we discuss scenarios that touch on common issues, including how those issues relate to the Code of Conduct, Statement of Principles, and Standard of Practice. Audience participation is highly encouraged. Come to see if you can guess what the “J” in the session title stands for!
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Moderators:
Julie Lederer
Panelists:
Madeline Main, Rick Sutherland
Demystifying Casualty and Cyber Risk Modeling
This session will include presentations on modeling both casualty and cyber risks.
Part 1:
Modeling has become an integral part of risk management but unlike natural perils like hurricanes and earthquakes, our understanding of the cyber threat is still in its early stages. This has created flawed attitudes that modeling isn’t ready to be an effective tool for estimating cyber risk. While there is much progress to be achieved, modeling capabilities are being used today within decision making workflows. In the first part of this session, you’ll learn how the challenges in modeling cyber risk are being overcome and how risk managers are taking advantage of modeling to better manage cyber risk.
Part 2:
Like cyber modeling, casualty catastrophe risk modeling is in its early stages. Traditional actuarial techniques, where historical claims data is used to predict future outcomes, does not adequately capture new and emerging risks. Scenario-based, forward looking models represent one way the inadequacies of traditional techniques can be overcome. In the second part of this session, we will discuss one approach to scenario-based casualty risk modeling, its primary business use cases, and the building blocks of a stochastic approach to the scenario-based casualty modeling framework.
Source:
2018 Ratemaking, Product and Modeling (RPM) Seminar
Type:
Concurrent Session
Panelists:
Scott Stransky, James Kaufmann