Tag Archives: craig

3 Ways to Measure Models’ Effectiveness

Most insurers are using some form of predictive modeling, but it can be difficult to know if it will remain effective over time. Evaluating a predictive model can be tricky because, while there are many ways data can be measured, there is no accepted standard. With the considerable investment that’s involved in predictive analytics, the C-suite understandably wants to hold certain yardsticks to the models and see if they are performing well, and to make sure every stakeholder is using it correctly. Having a forward-looking evaluation can make all the difference when making key decisions, especially if there is trust in the measuring mechanism.

Below are three new ways that insurers can evaluate the impact of predictive models, based on a model currently in production for a regional workers’ compensation insurer. The graphs below provide real-time insights that can help predictive modeling avoid becoming a black box, meaning that you can only see the output of the predictive model, not the input or how that output came to exist. The first two graphs separate out 10 equal portions of either premium or policy count, with each portion referred to as a “bin.”

1. Monitoring that a model is still current and accurate

You need to be able to regularly check if the model you have in production is still up-to-date and providing accurate scores. This graph illustrates the overall model lift on the book for a regional workers’ comp insurer in 2015 and 2016. The insurer’s model is generating a low score on business that’s running very profitably — the lower-risk bins 1, 2, 3 are approximately 30% better than average. Policies getting a score in the higher-risk bins 8, 9, 10 are all running at twice the average loss ratio. This provides a clear indication of what to target and what to avoid.

Bottom line: This model is still current and accurate.

See also: Top 6 Myths About Predictive Modeling  

2. Tracking the impact of a model on decision-making

To realize the benefits of analytics, your staff needs to leverage the insights to make more informed decisions that create improved results. This is a graph of “decision data” from Valen’s InsureRight Manage application. Orange represents policies that were declined, red is quoted and lost, green is quoted and bound and yellow represents non-renewals. It’s evident that declinations are low on the good business — less than 10% — and high on the other end, approaching 50% for bin 10. The insurer is not renewing policies in bins 9 and 10 and, most importantly, retaining more than 50% of business in bins 1, 2, 3.

Bottom line: Underwriters at this insurer are using the model to make more profitable risk selection and pricing decisions.

3. Measuring if the overall risk quality of a portfolio is improving with a model in production.

If you’ve established that your model is accurate and your people are using it, the next question is what kind of impact it’s making to the quality of your portfolio. Are we lowering the risk of our book of business? This view shows the insurer’s risk-selection trends, with an overview of how risk-selection decisions have been influenced by a model and the resulting change to the portfolio. The blue bars represent premium volume by month, and the orange line represents average risk score (i.e., loss ratio prediction) by month. Though there is some variability from month to month, the overall downward trend indicates improvement over the course of the year. There is a small uptick in December 2016, which provides an indication that further analysis is needed.

Bottom line: The risk quality of this portfolio is improving, though still requires careful monitoring.

See also: Survey: Predictive Modeling Lifts Profits  

Not only is it crucial to measure before an implementation takes place, it’s vital to do so both during and after, as well. Predictive modeling only works well if it is aligned with stated business goals, and knowing how to measure that is key to an insurer’s bottom line. With these three new ways to measure, insurers now will have different yardsticks to see whether it is successful and if they are using the actionable insights.

Applied Analytics Are Key for Progress

While most carriers collectively understand that predictive analytics is necessary to remain competitive with other data-driven and VC-backed companies, progress isn’t as fast as it should be. Some are still not using analytics at all despite knowing its importance, while many others limit use to one area of the business. One main obstacle is a disconnect between the C-suite and analytics staff.

The C-suite will not invest in initiatives they cannot measure, manage and understand. Therefore, how a business handles the implementation of analytics is just as important as the predictive models themselves. This is why applied analytics programs are needed to push the insurance industry into the future.

Applied analytics recognizes the value of data in specific business processes and basing key decisions off the insights. Carriers must define their strategy and goals around the initiative, decide on an implementation approach and convey it successfully to the rest of the organization to ensure buy-in and adoption. Executing this can be difficult, often a result of balancing sound technical decisions against each individual organization’s company culture.

Strategy and Goals

The first step a carrier should take when applying predictive analytics is building the strategy and selecting the goals. Beginning with smaller projects is often an excellent way to build confidence for future implementations across different areas of the business. In this phase, carriers decide which specific challenges they hope to tackle using predictive analytics. For example, a carrier’s main goal may be to improve risk selection and pricing, and a secondary goal would be to achieve underwriting consistency as the carrier grows its existing business in new states. By defining what the organization hopes to gain from a particular initiative, it avoids misunderstanding and confusion during the implementation and duration of the project.

See also: 3 Key Steps for Predictive Analytics  

Next, the carrier must choose their success metrics. Using the same example, if the target for a predictive analytics initiative is improving risk selection and pricing, loss ratio improvement is often the best measurement. If business growth is the primary concern, profitability and aligning price-to-risk is an important metric to use. The C-suite is results oriented and this step sets the foundation for the implementation that follows.

Implementation Plan

Once a project has been selected, its goals determined and success metrics defined, an implementation plan should be created to strategize the role governance will play within the corporate culture. The way a carrier must address this step largely depends on the type of predictive analytics initiative in place. If a commercial auto carrier uses analytics to improve pricing with its long-haul trucking business, it’s key to find the balance between the model score and your underwriters’ expertise. Don’t leave it to chance, carriers should develop clear rules for how to use the predictive model that matches each company’s weaknesses and strengths.

By using the predictive model, policies are scored individually and assigned to a specific risk “bin”.

As one example, a carrier may decide that the best performing risks for smaller policies (bins 1-3) are approved for straight through processing, the average risks (bins 4-7) must always be reviewed by underwriters, and the poorer performing segments (bins 8-10) should be avoided altogether. A common and more granular form of implementation is determining how much credit or debit can be added to each policy depending on the model score, before needing management approval. By implementing rules of engagement that correctly fit a specific organization, it will not only boost the effect of the predictive analytics project but make it easier to manage and make necessary adjustments long-term.

Organization Adoption

Even if a carrier has an excellent strategy and model, it means nothing if those who will be using it on a daily basis fail to do so correctly. During the implementation process, all members of the organization must be aligned with project goals and comprehend its importance for the company. This means undergoing training and support by those involved closely with the initiative — whether the model is being built in-house, through a third party vendor or a consultant. There should be complete transparency throughout the process, and room for adjustment based on feedback from the staff. Predictive analytics is an imperative tool in its own right, but just like any tool, it requires a skilled individual to obtain the best results. In fact, Valen research shows the best results are found when combining human judgement and predictive analytics.

The graph shows the lift of a predictive model. The greater the lift, the more effective the model is for the carrier. The blue line represents the loss ratio improvement based on a combination of the underwriter and the model when making decisions on pricing policies. There is clearly a more significant lift here when compared to both the underwriter (green) and predictive model alone (red).

See also: An Opportunity in Resilience Analytics?  

In order to sustain long-term plans and goals, the predictive analytics strategy must converge with the overall corporate strategy. That can’t happen for any real length of time without executives confidently making important decisions using the insights that come from predictive modeling. Only when a carrier and all of its members fully understand those insights and trust in data are they able to become a data-driven organization.

A New Frontier for Venture Capital

With sales of ping pong tables declining and with first-quarter IPO numbers the lowest since 2008, many are wondering whether we are in the midst of another tech bubble and, if so, when it will burst. Despite a record amount of money flowing into venture capital, funding for startups is drying up.

Rather than believing in every single unicorn, VCs need to believe in insurance. As insurance tech investment has skyrocketed ($2.65 billion in 2015) and is expected to increase in 2016, a shift in how money is invested in Silicon Valley is beginning to take place. Investors are jumping into the insurance tech ecosystem, and, as software is increasingly pervasive in the industry, insurance startups are attacking a wide range of different pain points. Given the rapid expansion in available information, artificial intelligence and IoT technologies, innovative carriers and data-rich competitors from outside the industry may be poised to spark transformations in a number of insurance markets. From commercial auto and health aggregators to providers and solutions, the space is rapidly growing.

Why Invest?

For starters, insurance has the two components any VC-backed startup longs for: 1) Poor customer experience issues across the board and 2) an industry that has been necessary since the 1800s. While venture capitalists and entrepreneurs have been investing and building new offerings, this seems odd to others because, from a consumer perspective, the insurance industry is highly regulated and mundane. But insurance is — and will always be — in demand because people and businesses are looking for ways to minimize risk. Let’s not forget that the industry contributes close to 8% GDP in the U.S. and employs more than 2 million people.

Insurance represents a significant part of the S&P 500 index and has seen a ton of M&A growth ($13 billion) in 2015 alone. Even though it is overlooked for a variety of reasons — regulations, low profit margins, lack of innovation, etc. — technology’s influence is providing the industry with changes that are necessary to stay afloat. Now, consumers can shop for better rates and compare prices easily, while agents and underwriters can better manage data and provide more precise quotes.

The workforce is also changing significantly, and the option for working outside of the traditional employer relationship is on the rise. Individuals need insurance and traditional models are ill-suited to accommodate, so it’s no wonder newer models are coming out of the woodwork to capitalize on this need for change. The workforce inside the industry is changing as well, with the average age of an agent at 59 and with one-fourth of the workforce expected to retire by 2018. Companies are targeting millennials in hopes of boosting numbers and more changes.

While VCs have typically avoided regulated industries, the revenue base in insurance is incredibly high, and investors are paying attention. Because of disruption, M&As, the widespread consumer dissatisfaction with dominant carriers and the Affordable Care Act’s new marketplace for individual plans, innovators are jump-starting a revolution.

Time-to-Invest Indicators

The commercial lines insurance market is starting to undergo the same kind data analytics revolution that first occurred in personal auto, which caused market consolidation over the past two decades. From 1970-92, Progressive averaged a 3% annual profit margin on underwriting insurance, whereas its competitors averaged a 7% annual loss. In 1992, Progressive had $1.45 billion in premium — it now holds $16.5 billion in premium. By implementing predictive analytics, Progressive’s pricing sophistication adversely selected competitors, and the company was able to gain considerable market share. Today, the top 10 personal auto carriers represent 71% of the market. Workers’ compensation, which is often considered the leading indicator for momentum across all of commercial lines, already has companies showing signs of a market share shift.


The above graph shows several companies’ growing market share from 2009-14, with notable gains from analytically-driven companies like Berkshire Hathaway and Travelers.

Something else to keep an eye out for is the important connection between the Internet of Things (IoT) and insurance. IoT is influencing just about every industry, and it’s been predicted that, by 2020, IoT will reach a billion dollars. From driverless cars to connected homes, IoT is already hitting insurance. Liberty Mutual just acquired IoT startup Notion to help reduce water leakage and burglaries, while State Farm is already offering discounted rates to homeowners who have a Nest thermostat or smoke detector. Insurance companies are interested in these technologies because they ultimately provide better benefits to the customer.

Another reason to invest in insurance is simply that carriers themselves are investing. Insurers, who arguably have the best view of their own business and the complexities that come with it, are increasingly recognizing technology’s potential to offer real-time monitoring of vehicles, homes and all other areas of risk exposure. The main ways carriers are doing it now is by investing in emerging startups and tech giants — and even creating innovation and VC organizations internally.

From emerging tech trends to market share consolidation, insurance investment is rapidly growing. According to data from CB Insights, the first quarter of the year was the second largest ever for investment in insurance technology with more than 45 deals raising $650 million.

The industry is growing fast — with deals, acquisitions and innovations — and we can expect to see more traction in the next few years.

Start-Ups Set Sights on Small Businesses

When start-ups jumped into insurance, many focused on the personal auto industry. Not surprising, considering it is arguably the least complex line of insurance and is often the first to be disrupted (going back to Progressive in the ‘90s). Now that InsurTech investment is at an all-time high, more start-ups are entering the market and have become increasingly confident in their ability to tackle complex lines of business. If recent start-ups like CoverWallet and Next Insurance are any indication, small commercial business is the next line to face aggressive disruption. If carriers want to stay competitive and grab profitable market share, they will have to adapt to today’s standards for the customer experience.

Small Commercial an Obvious Move for Startups

Targeting the small commercial business market makes sense, given a recent McKinsey study that calls the line “one of the few bright spots in P/C insurance.” The study points out that, since the 2008 recession, the number of small businesses has grown, and 40% of sole proprietorships don’t have insurance.

Unfortunately for the traditional carrier, the majority of small businesses are also open to purchasing policies online. But remember that saying you’re open to purchasing online and actually purchasing online are two very different things – especially if we use the recent past as an indicator.

See Also: So Your Start-Up Will Sell Insurance

Google Compare terminated operations after sluggish growth across the U.S., with many of their leads failing to purchase. This is not atypical for this insurance shopping method. Several years ago, Overstock also tried selling insurance online outside of personal auto – including commercial business – and that closed down quickly.

That two business giants failed doesn’t mean online purchasing won’t eventually catch on. Start-up culture is largely a test-and-learn environment.

But these initial growing pains do indicate that traditional insurance still has a chance to stay alive amid disruption if they provide an efficient, engaging consumer experience.

Consumers Want Both Confidence and Efficiency

It’s not that consumers don’t want to work with carriers and agents, it’s that the customer efficiency of 30 years ago is no longer an appropriate benchmark. Of course small business owners are open to purchasing online, because traditional insurance has not yet given them the experience they desire. According to a PIA study from last year, small commercial businesses would much prefer the personal attention from agents (and by extension the carriers they work with) as long as they do a better job of adapting to technologies and the Internet. From the customer’s perspective, an experience with an insurance carrier isn’t compared only with other carriers – but to other companies they do business with regardless of industry. Whether it’s Amazon, Apple, Google, etc., your customer experience will be rated against the companies leading in the modern, digital world.

This explains many of the start-ups entering the space now and why they have the potential to gain the upper hand.

To achieve better communication, carriers need to think more broadly about their usage of data and predictive analytics. You have to gain an incredibly detailed view of your customers, their behaviors and their responses to your communication and product offerings. We always recommend an incremental rollout of analytics to get your feet wet before diving in. At the same time, it’s critically important to be ready to build off that early momentum and develop an overall predictive analytics strategy that seamlessly merges with business goals. Recognize that this evolution to becoming more data-driven is as much about organizational change as it is about technology.

When carriers understand how predictive analytics benefits them, they can confidently make data-driven decisions that improve every aspect of their business – including the customer experience. For example, using underwriting analytics to achieve real-time insights into pricing policies doesn’t just help a carrier’s bottom line – it also greatly streamlines and expedites the communication chain between consumers, agents and carriers.

At the recent Dig In insurance conference, a panel of InsurTech CEOs discussed how start-ups dissect insurance data – in ways that differ from traditional insurers and agents. A member of the audience asked, “Why are start-ups so combative in their approach?” It was an intriguing question that highlights the digital divide in terms of how the industry thinks about evolving versus how technology and Internet entrepreneurs think about playing in industries ripe for disruption. What feels “combative” to the incumbent is often seen as “customer-centric” to the new entrant.

It’s important that carriers understand that there is a way to co-exist, but counting on new entrants to accept the status quo is a bad bet. Think of start-ups as an advocate for a better customer experience, and see those that fit your business as innovation partners. Adopt the mantra that the customer always wins, and you’ll remain relevant in the customer value chain.

3 Ways to Boost Trust in Your Brand

It’s no secret that there is a newfound aggressive and competitive environment in insurance. A combination of outside competition focused on disrupting the distribution channel and an increase in tech-driven carriers is fostering this environment, and adapting to this change goes beyond just adopting technology. Everything hinges on a carrier’s ability to shed its conservative approach to business – both internally and when communicating to customers.

Although fairly new in the U.S., insurance price comparison sites are rising in both popularity and sophistication, enabling consumers to compare policies from insurers down to the last dollar in a matter of seconds. Carriers shouldn’t fear these sites but should be prepared with a strategy that allows them to stay successful amid this disruption.

Regardless of the changes happening, insurance still remains a complex purchase, and brand trust is a valuable way to differentiate your company. Nicholas Weng Kan, CEO of Google Compare, shares that there is a level of comfort that customers need before they make the commitment to buy a policy; that is why more than half of sales still happen after a conversation with an insurance expert.

So how do you gain trust for your brand? The catalyst for success in modern business is through transparency, which breeds trust – something insurance desperately needs. According to a recent Ernst & Young study, insurance suffers from lower levels of trust than any other industry, with 57% of consumers expressing dissatisfaction at the lack of interaction from their insurer.

Below are steps carriers can take to elevate trust in their brand:

First Step: Get to Know Your Customer

An important aspect of successful businesses today is the ability to create a relationship with the customer. Carriers don’t have the bandwidth to treat each customer with interpersonal attention but can still understand who they are and what they want. Through the use of analytics, carriers have quick access to valuable information about a customer. Brands that don’t begin adopting these technologies to match customer needs can’t keep up with those that do.

Netflix obliterated Blockbuster by using advanced analytics to know customers better. The same dynamic differentiates between the data-driven and traditional carrier: Once the customer acquisition approach is more segmented and targeted, carriers can also deliver the right price based on a more accurate risk profile.

While pricing may not be everything, competitive pricing is necessary. The E&Y survey found that 50% of consumers change their insurer because of price. Insurance is already a complex business that lacks linearity, and price is an important consideration for all customers. The most competitive carriers leverage predictive analytics as a useful tool to help distinguish the poor risks from the good risks so they can focus on the customer relationships that will benefit their business in the long term.

Second Step: Learn to Cater to the Millennial Generation

Millennials have overtaken the baby boomers as the largest consumer base in the country, at 75.3 million strong, and it is clear that they aren’t satisfied with the insurance buying process. According to the 2015 Capgemini World Insurance Report, less than 30% of insurance customers around the world enjoy a positive customer experience, with North America seeing the deepest decline in satisfaction.

Millennials crave transparency and a buying process that is painless and streamlined. Trust is bred when they know their insurers have their best interests at heart and care about their well-being, as well as the causes that are important to them. Above all, Millennials demand efficiency and personalization. Using innovative technologies to interest and retain Millennials is key to gaining their trust. Not only will this breed a positive experience, but it limits the amount of confusion from the consumer, thus creating fewer touch points for the insurer or agent.

Last Step: Be Transparent

The industry holds tightly to how products and services are priced. That’s just not going to work any more. Customers are sophisticated and expect insurance agents to connect them to information. Agents and insurers won’t garner consumer trust with a “black box” buying process.

Consumers have moved on from the notion that they are better off when an expert makes choices for them, but they do want to be guided by experts and understand what is happening in each step of the process. According to another E&Y study, nearly 70% of global customers feel they initiate the purchase of new policies because of the availability of digital channels. Based on results, it was inferred that difficulty in accessing information contributes to customers leaving their current carrier.

If insurers continues to be secretive about how they conduct business and price their policies, then many of the new insurance innovations run the risk of being perceived negatively by consumers. For example, Internet of Things has broken into homeowners, with partnerships between Nest and well-known insurers such as Liberty Mutual, but if the pricing structure and benefits aren’t clearly defined, there is a chance of a consumer backlash.

A Consumer Reports article earlier this year found that insurance is receiving criticism for using credit information to price personal auto policies. Of course, credit information is a strong indicator of loss and a smart predictive factor for any auto insurer, and it’s used by many different industries. However, there is perceptual damage, leaving the industry blindsided by critics who assume that secrecy must automatically mean untrustworthy.

Insurance needs to find the right balance between doing a good job managing risk and developing a more innovative and transparent culture. Creating a positive consumer experience involves being more transparent about price and clearly defining the benefits and service offered by the carrier. Almost 40% of consumers are either not confident or only somewhat confident that they have the appropriate coverage. This should be a wake-up call to the industry that all aspects of customer engagement need attention.