Tag Archives: valen analytics

Top 6 Myths About Predictive Modeling

Even if you’ve been hiding under a rock the past 25 years, it’s almost impossible to avoid hearing about how companies are turning around their results through better modeling or how new companies are entering into insurance using the power of predictive analytics.

So now you’re ready to embrace what the 21st century has to offer and explore predictive analytics as a mainstream tool in property/casualty insurance. But misconceptions are still commonplace.

Here are the top six myths dispelled:

Myth: Predictive modeling is mostly a technical challenge.
Fact: The predictive model is only one part of the analytics solution. It’s just a tool, and it needs to be managed well to be effective.

The No. 1 point of failure in predictive analytics isn’t technical or theoretical (i.e., something wrong with the model) but rather a failure in execution. This realization shifts the burden of risk from the statisticians and model builders to the managers and executives. The carrier may have an organizational readiness problem or a management and measurement problem. The fatal flaw that’s going to derail a predictive analytics project isn’t in the model, but in the implementation plan.

Perhaps the most common manifestation of this is when the implementation plan around a predictive model is forced upon a group:

  • Underwriters are told that they must not renew accounts above a certain score
  • Actuaries are told that the models are now going to determine the rate plan
  • Managers are told that the models will define the growth strategy

In each of these cases, the plan is to replace human expertise with model output. This almost never ends well. Instead, the model should be used as a tool to enhance the effectiveness of the underwriter, actuary or manager.

Myth: The most important thing is to use the right kind of model.
Fact: The choice of model algorithm and the calibration of that model to the available data are almost never the most important things. Instead, the biggest challenge is merely having a credible body of data upon which to build a model. In “The Unreasonable Effectiveness of Data,” Google research directors Halevy, Norvig and Pereira wrote:

“Invariably, simple models and a lot of data trump more elaborate models based on less data.”

No amount of clever model selection and calibration can overcome the fundamental problem of not having enough data. If you don’t have enough data, you still have some options: You could supplement in-house data with third-party, non-insurance data, append insurance industry aggregates and averages or possibly use a multi-carrier data consortium, as we are doing here at Valen.

Myth: It really doesn’t matter which model I use, as long as it’s predictive.
Fact: Assuming you have enough data to build a credible model, there is still a lot of importance in choosing the right model — though maybe not for the reason you’d think.

The right model might not be the one that delivers the most predictive power; it also has to be the model that has a high probability of success in application. For example, you might choose a model that has transparency and is intuitive, not a model that relies on complex machine-learning techniques, if the intuitive model is one that underwriters will use to help them make better business decisions.

Myth: Predictive modeling only works well for personal lines.
Fact: Personal lines were the first areas of success for predictive modeling, owing to the large, homogeneous populations that they serve. But commercial lines aren’t immune to the power of predictive modeling. There are successful models producing risk scores for workers’ compensation, E&S liability and even directors & officers risks. One of the keys to deploying predictive models to lines with thin policy data is to supplement that data, either with industry-wide statistics or with third-party (not necessarily insurance) data.

Myth: Better modeling will give me accurate prices at the policy level.
Fact: Until someone invents a time machine, the premiums we charge at inception will always be wrong. For policies that end up being loss-free, we will charge too much. For the policies that end up having losses, we will charge too little. This isn’t a bad thing, however. In fact, this cross-subsidization is the fundamental purpose of insurance and is necessary.

Instead of being 100% accurate at the policy level, the objective we should aim for in predictive analytics is to segment the entire portfolio of risks into smaller subdivisions, each of which is accurately priced. See the difference? Now the low-risk policies can cross-subsidize one another (and enjoy a lower rate), and the high-risk policies will also cross-subsidize one another (but at a high rate). In this way, the final premiums charged will be fairer.

Myth: Good models will give me the right answers.
Fact: Good models will answer very specific questions, but, unless you’re asking the right questions, your model isn’t necessarily going to give you useful answers. Take time during the due diligence phase to figure out what the key questions are. Then when you start selecting or building models, you’ll be more likely to select a model with answers to the most important questions.

For example, there are (at least) two very different approaches to loss modeling:

  • Pure premium (loss) models can tell you which risks have the highest potential for loss. They don’t necessarily tell you why this is true, or whether the risk is profitable.
  • Loss ratio models can tell you which risks are the most profitable, where your rate plan may be out of alignment with risk or where the potential for loss is highest. However, they may not necessarily be able to differentiate between these scenarios.

Make sure that the model is in perfect alignment with the most important questions, and you’ll receive the greatest benefit from predictive analytics.

New Data Strategies for Workers’ Comp

Workers’ compensation is widely recognized as one of the most challenging lines of business, suffering years of poor results. Insurance companies are under increasing pressure to achieve profitability by focusing on their operations, such as underwriting and claims.

Insurers can no longer count on cycles, where a soft market follows a hard one. The traditional length of a hard or soft market is evolving in a global economy where capital moves faster than ever and competitors are using increasingly sophisticated growth, segmentation and pricing strategies.

Insurance executives also cite regulatory and legislative pressures, such as healthcare and tax reform, as inhibitors of growth. Furthermore, medical costs continue to rise, making it particularly difficult to price for risk exposure. The long tail of a workers’ compensation claim means that the cost to treat someone continues to increase as time elapses and becomes a compounding problem.

Despite recent improvements in combined ratios, there are still many challenges within workers’ compensation that have to be reconciled. The savviest insurers are evaluating the availability of technologies, advanced data and analytics to more accurately price risk – and ultimately ensure profitability.

The ‘Unknown’ in Workers’ Compensation

Information asymmetry has made it difficult for insurers to accurately determine who is a high-risk customer and who is low-risk. At the point of new business, a workers’ compensation insurer is likely to have the least amount of information about those they are insuring, and it’s easy to understand why. The insured knows exactly who is on the payroll and what types of duties employees have. Some of that information is relayed to an agent, and then finally to the carrier, but, as in any game of telephone, the final message becomes distorted from the original.

This imbalance of information is one reason why fraud is rampant, and why insurers ultimately pay the price. Payroll misclassification – or “premium fraud” – occurs when businesses pay salaries off the books, misrepresent the type of work an employee does or purposely misclassify employees as independent contractors. Some misclassifications are not nefarious. But whatever the cause, they create significant revenue and expense challenges for carriers that rely on self-reporting.

The ‘Silent’ Killer

Without the right insight or analytical tools, insurance companies have a hard time discerning between their policyholders and making consistent and fair decisions on how much premium to charge on each policy. When an insurer begins to use predictive analytics, competitors that are still catching up run the risk of falling victim to adverse selection. When we hear executives say things like, “The competition has crazy pricing,” it raises a red flag. We immediately begin looking for warning signs of adverse selection, such as losing profitable business and an increasing loss ratio.

The problem is that it takes time to recognize that a more sophisticated competitor is stealing your good business by lowering prices while also sending you the worst-performing business. By the time you recognize adverse selection is occurring, you’re falling behind and have to respond quickly.

The Power of Actionable Data

Fortunately, there are technologies available for insurers of all sizes to make more informed, evidence-based decisions. But when it comes to data, there is still some confusion: Is more data always better? And how can carriers turn data into actionable results?

It’s not always about the volume of data that an insurer has; it’s about the business value you can derive from it.

If an insurer is just beginning to store, govern and structure its data, it is likely not receiving actionable insights from historic data assets. Accessing a more holistic data set with multiple variables (from states/geography, premium size, hazard groups, class codes, etc.) through a third party or partner can help to avoid selection bias, while encouraging rigorous testing and cataloging of data variables. Having access to a variety of information is key when it comes to making data-driven decisions.

The conundrum insurers face when delivering actionable intelligence that underwriters can use is that they only know the business they write. They know very little about business they quote and nothing about business they don’t even see. What complicates this picture is that an insurer’s data is skewed by its specific risk appetite and growth strategies. It’s up to the insurer to fill in the blind spots in its own data set to ensure accurate pricing and risk assessment. As we know, what an insurance company doesn’t know can hurt it.

As insurers increasingly turn to advanced data and analytics, the next question that keeps insurers up at night is, “When everything looks good, how do I know what isn’t really good?” One way that Valen Analytics is helping insurers answer that question is by providing companies with a “Risk Score,” a standard measure of risk quality. By tapping into Valen’s contributory database, workers’ compensation underwriters can have better insight into all the policies they write – even historically loss-free policies. In fact, the Risk Score accurately identifies a 30% loss ratio difference between the best- and worst-performing loss-free policies. This is one example of how the power of data can push the industry forward.

Despite its many challenges, the workers’ compensation industry is becoming more analytically driven and improving its profitability. A comprehensive data strategy drives pricing accuracy and business growth while allowing insurers to achieve efficiencies in underwriting decision-making. By keeping up with technological advances, insurers can use data and analytics to grow into new markets and areas of business, while also protecting their profitable market share.

While NCCI’s annual “State of the Line” report labeled workers’ compensation as “balanced” this year, we may soon see the integration of data and analytics push the industry to be recognized as “innovative.”

Data, Analytics and the Next Generation of Underwriting

There appears to be violent agreement that 2014 is the year of advanced technology, data and analytics in insurance. Of course, these kinds of prognostications don’t sneak up on anyone. A convergence of growing organizational eagerness and sophisticated tools is allowing momentum to build for the next generation of underwriting to emerge.

Market dynamics are always an important factor in what ultimately makes the cut from strategic planning to implementation. The investment environment, increasing regulatory pressure and rising costs are influencing a more analytical approach to underwriting to increase profitability. With its historically volatile performance, homeowners insurance will be a particular focus in personal lines this year, as carriers adopt new approaches to drive profitability through underwriting.

2014 will provide a focus on shoring up the foundation needed to enable insurers of all shapes and sizes to become more analytically driven. And while carriers make progress, securing the necessary talent needed to succeed is a growing and industry-wide concern.


Shifting Focus Toward Homeowners, Following Trends in Auto Market

Analysis of the auto insurance market proliferated at the end of 2013, with some declaring pure direct writer Geico the inevitable winner in the “battle of the titans” against Progressive and other major players because Geico is unencumbered by an agency force. Time will tell if that’s the case, but one thing is clear: Scaling profitable market share in auto can only be done by technology focused and analytically driven carriers, with substantial marketing resources.

The trends in the auto market foreshadow what other lines of property and casualty insurance will face in 2014 and beyond, most urgently in homeowners. Consumer demand for online shopping increases pricing competition and customer-acquisition costs and at the same time lowers retention rates – the combination of which can squeeze margin for carriers that do not have advanced pricing tools. This dynamic forces insurers to sharpen their pencils and produce strategies to differentiate their brands and gain a competitive advantage. For carriers not as advanced as the larger auto carriers, the dynamic can represent fundamental shifts in their business and operating models.

Partially because of continuing market share consolidation and pricing stagnation in auto, there is increasing focus on homeowners insurance. A recent report by Aon Benfield shows 15% growth in direct written premium for homeowners between 2009 and 2012, compared with just 6.5% for direct personal auto premium. With the historical volatility and poor performance of the homeowners line of business, a number of new underwriting approaches are entering the market. At the same time, the industry is adapting to a changing consumer and regulatory landscape.

Consumer Demographics Changing the Game

“Show me the money (i.e., discounts), give me all the info I need wherever I am and in real time, and make sure your customer service is stellar or I’ll write up what a horrible experience I just had in 140 characters and share it instantly with all my friends.”

Exhausted yet?

The Millennial generation, at 77 million strong, demonstrates very different buying behaviors and demographic patterns than previous generations. These young consumers are having a notable impact on personal lines insurers. They primarily choose urban living, with very little difference between those who are parents vs. non-parents, according to a study from the American Public Transportation Association. They are less likely to drive cars and prefer multiple modes of transportation. In fact, a study from USA Today shows that Millennials are less concerned about owning either a home or a car.

This budget-conscious generation is reacting to the dismal economy and job market they encountered upon entering the workforce, as well as the significant levels of student loan debt many of them carry. They are much more sensitive to taking on long-term debt and minimizing monthly expenses. Because they have a job-scarcity mentality, Millennials value being unburdened in case they need to relocate for their career.

These trends also affect home building. While the news about housing starts is promising (up 22.7% in November 2013), real estate developers are responding to the Millennial generation’s desire for high-density urban living and hesitancy to commit to a mortgage – at least for now. While no one can predict how the home-ownership trend will play out for the long term, the insurance industry needs a product mix and customer-service approach that meets the needs of this demographic population.


Advancements in Advanced Data & Analytics

Traditional property inspection methods being used today only deliver an actionable result 25% of the time, which means 75% of inspections are a waste, according to a Claims Journal study. This ineffective use of resources isn’t sufficient to address the profitability issues that have plagued this line of business for years. In fact, since 1990, the homeowners industry has only experienced four years with combined ratios below 100. To combat the high combined ratios, carriers divide losses into two categories – catastrophe and non-catastrophe – and continually perform analyses to determine what characteristics about a home, the insured and the weather have the greatest impact on controlling losses.

Again, the auto insurance industry shines as being out in front of the P/C market with usage-based insurance and data collection on individual behavioral attributes. While it’s still an uphill battle for consumer adoption, the technology momentum is here to stay. Insurers are leveraging new data sources and analytical insights to improve their strategic approach to marketing, underwriting and claims.

For the full white paper by Valen on this topic, see their website.

3 Reasons Why Millennials Should Embrace a Career in Insurance – And Why Insurance Needs Them

The insurance industry faces an urgent need to attract a new generation with new talent. According to the U.S. Bureau of Labor Statistics and AARP, within 15 years as much as 50 percent of the current insurance workforce will retire. In addition, the industry is changing so fast that it can no longer rely on traditions and standard practices; insurance requires new ideas and new skills.

While all industries eventually face a time when there is a passing of the baton from one generation to the next, insurance is taking a hit now because we have an older than average workforce. So, we must engage with so-called Millennials to show that insurance is, in fact, an innovative and rewarding industry to work in.

In the early 1990s, when the California dairy industry faced a similar dilemma, it came up with the “Got Milk?” campaign. The campaign resonated with an important demographic, kids aged 12-18, who were being drawn away from milk by massive brand campaigns from providers of other beverages. The campaign was wildly successful, reinvigorating milk sales after three decades of declines.

The insurance industry needs the equivalent of a “Got Milk?” branding campaign. It needs to contain three key messages:

1. Insurance is an increasingly savvy industry.

Insurance carriers have had to adapt and evolve for centuries. Today, insurers are incorporating cutting-edge technology, including big data and predictive analytics. Tech is becoming a mainstay in the industry.

Companies such as Vodafone and Burberry have shown how data can transform marketing, and insurers will follow their example. As a whole, the industry will become much more innovative.

So, the industry should be enticing not just to young talent who are inherently tech-savvy and creative but also to those students who have a history in STEM (science, technology, engineering and mathematics).

2. Insurance is a sustainable industry.

In an unstable and uncertain economy, insurance has longevity on its side. As long as people continue to drive cars, buy homes and, simply, work, there will always be a need for auto and homeowners insurance and workers’ compensation. Insurance offers job security for Millennials who may be nervous about the fluctuating job market.

The insurance industry also provides a unique opportunity for young people to establish a solid foundation for a career with room to grow. Whether someone wishes to be an underwriter, an agent, or an actuary, there is a little something for everyone. Millennials tend toward “job hopping,” and insurance can provide young people with enough internal mobility to maintain their interest while keeping them within the industry.

3. Insurance is a service industry.

The insurance industry serves an important common good by allowing all of us to share risk for a small fee (premium) so that an accident or a storm does not ruin people financially. Without insurance, most people wouldn’t be in the financial position to start a business, own a home or even have a car. The core purpose of insurance meshes well with the interests of Millennials, 63% of whom volunteered for a nonprofit in 2011, according to the Millennial Impact Report. People who have a passion for helping others might welcome being a customer service representative and being the first point of contact at an insurer or might enjoy being an underwriter and ensuring that insurance policies are accurately written to provide a customer with the best protection.

Moreover, as young people’s talents and passions are brought into the industry, insurance carriers can expect to become better at what they do. In other words, the expertise stemming from new generations will allow for more accurate and, most importantly, more responsible insurance practices when handling scenarios such as relief from natural disasters.

The insurance industry truly makes a difference in people’s lives, often during difficult times. Young people can transfer their compassion into a career that delivers tangible results not only for themselves but for other people, too.

How will we attract and lead the new generation?

Where do we go from here? How do insurance companies draw talent when the competition is so fierce?

The first step is to use the tools we have – each other. The insurance industry can unite to overcome this talent crisis and collectively focus on appealing to the Millennial generation. An example of collaboration is Tomorrow’s Talent Challenge – an initiative involving industry leaders to motivate college students to explore the career potential in insurance analytics and technology.

We must also recognize that Millennials are looking for leadership they can relate to. Insurers need to hire people with titles such as chief decision scientist and chief data officer to head new departments of digitally savvy experts, if insurers are to draw young, tech-savvy talent. Creating and filling these roles will not be easy. According to McKinsey, by 2018, global demand for technical and managerial talent will exceed supply by 50 to 60 percent. We need to start working on the problem now.

If we as an industry can attract the right senior-level talent, can effectively communicate the professional and personal benefits we can offer to young people, and can articulate the creative contributions they offer us, then we will be on the right track for everyone to be asking the important question:

Got Insurance?

The Coming Consolidation in P&C Insurance

A weak economic recovery and regulatory issues are providing significant challenges to traditional business models in property and casualty insurance, especially in commercial lines. Carriers can no longer rely on investment income, and market-share consolidation should be a growing concern leading into 2014.

History tells us that the winners will be companies that are more progressive in their use of new operating models and tools, including advanced data and analytics.

Nigel Morris, managing director of QED investors and co-founder of Capital One, recently said: “In the late ‘80s and early ‘90s, Capital One was at the vanguard of a revolution deploying data-driven strategies in the credit card industry … I believe that insurance carriers increasingly have the same opportunity to grow the size and profitability of their businesses by more specifically meeting their customer’s needs.”

The credit-card industry shows what might happen in P&C. During that time in the late 1980s and 1990s, new marketing and risk-assessment strategies fundamentally changed the credit-card industry. Technology and information-based companies like Capital One flourished and garnered significant market share while those that clung to traditional methods floundered. The agent of change? Analytics. In 1988, Capital One (originally Signet Bank) was founded because it saw an untapped opportunity to leverage credit-score and consumer-spending patterns to find the best risks within the subprime market and revolutionize the credit-card industry.

Similarly, Progressive Insurance pioneered the use of analytics, also leveraging credit scores, to insure nonstandard risks at profitable rates and shake up the auto-insurance market.

The adoption of sophisticated technologies essentially creates a perfect storm. Those who use the best analytics create positive selection, gaining profitable market share. Those who don’t use analytics suffer from adverse selection, ending up with poorer-performing risks because they are working with outdated pricing and risk-assessment strategies.

As Matthew Josefowicz, managing director of Novarica, wrote in a recent report, “The massive proliferation of easily accessible data combined with the increased power of modern analytical tools has the potential to transform the insurance industry dramatically over the next decade. The strategy and operations of insurers in the near future could be nearly unrecognizable to current market leaders.”

Data and analytics will only continue to evolve and change the way business is done, whether it’s in insurance, banking, healthcare, shopping or another industry; the accessibility to personal information is truly transforming the world we live in and how we do business.  In the insurance world, companies like Valen Analytics are creating solutions and providing insights to help drive overall success, for instance by helping carriers manage and segment their portfolios to drive underwriting profitability.

Valen’s 2014 Outlook: Commercial Lines report sheds light on the industry’s top challenges and offers information to help better prepare and adapt for 2014; it is available in full here.