Best Time to Implement Predictive Analytics in Insurance?

When Is the Best Time to Implement a Predictive Model?

News of carriers implementing predictive analytics has been relatively widespread the past several years. Even if you’ve been hiding under a rock, it’s almost impossible to avoid hearing about how companies are turning around their results through better modeling or how new competitors like Lemonade and Zenefits are entering into insurance using the power of predictive analytics. It’s difficult to know when to begin, especially when implementation seems like a daunting task.

So, when is the best time to adopt predictive analytics and implement a predictive model?

The answer is simple: Now. Here’s why:


Market share consolidation is happening.

We’ve already seen the personal lines market become consolidated and now commercial lines are following suit. It’s no coincidence that the historically troubled line of workers’ compensation only became profitable for the first time since 2006, while significant shifts in market share appear among the top 10 insurers.

Companies such as Travelers and Berkshire Hathaway are known to have a well-established holistic analytics strategy driving their businesses and have developed a more targeted and sophisticated customer acquisition strategy in order to locate the best risks and price them competitively.

Adding to the consolidation issue is the continued growth of mergers and acquisitions on a global scale, with the U.S. showing the most activity at a 61% year-over-year increase. Commercial insurers need to arm themselves with more data so they can compete with companies targeting niche markets and leveraging more granular segmentation of mainstream business.

Having the tools needed to compete for this business is crucial to staying ahead of the pack during a tumultuous period of change in the industry.


Outside competition is coming into insurance.

Think you’re only competing against other insurance carriers? Think again. Investment in insurance technology more than tripled from 2014 to 2015, with a whopping $2.6 billion last year. Industry giants like Progressive and USAA are known for their innovation and analytics approaches, but there are new players on the horizon with the likes of Lemonade, Coverhound, Policy Genius, Everquote, and Zenefits, just to name a few.

All of this innovation comes at a time of immense disruption in response to the overall lack of customer satisfaction with the insurance industry. With an average industry-wide Net Promoter Score of 28 (out of 100), the fact is that we as an industry are not living up to customer expectations. This gap in satisfaction means that competitors who can offer a streamlined, efficient experience can swoop in and show customers what they’ve been searching for.


Your internal teams are fighting each other over price.

Pricing has never been more important than it is right now. Thirty years ago, carriers could earn a 16% ROE by simply breaking even on the underwriting side. Now, with lower investment yields and lower leverage, a 100% combined ratio delivers an anemic 3.5% ROE. To make profitability targets, carriers have to be making a profit on the underwriting side. There is no other option.

However, in a recent survey we conducted with over 200 P/C insurance professionals, we found that 77% believe that actuaries and underwriters are at odds over price. Setting prices has traditionally been seen as the domain of the actuary. But, you also need smart risk selection, which is the art of underwriting – knowing whether to accept the risk under consideration at prices being set by the market. If they’re working in opposite directions, you’re going to go in circles.


Your customers are demanding immediacy.

With advances in technology, people have become accustomed (and conditioned) to faster and faster responses, which means underwriters are squeezed for time and have to generate quotes much quicker than they used to.

Consider these examples:

  • FirstComp conducted an in-depth study of response times to closing workers’ comp business. They found that when an insurer provides a quote to an agent within one hour, the quote-to-bind ratio is 52%. However, if you wait 24 hours, it drops to 30%. Think back 5-10 years. Would anyone have talked about a 20% drop in the quote-to-bind ratio because an agent had to wait just one business day?
  • Zurich, understanding this trend in customer expectations, cut the time required to give a commercial auto quote on a 100 vehicle fleet from 8 hours to just 15 minutes. That wasn’t their only win here – now their underwriters can focus on applying their expertise (actually underwriting) instead of spending time gathering and entering data.

Both of these examples are from 2012, so imagine how much has changed in just 4 years.


Your competition is already using predictive models to adversely select against you.

Adverse selection blindsides many carriers with devastating consequences on their portfolios as early adopters have already started to become much more sophisticated in their pricing. Companies that underwrite and price based on traditional methods are competing against these early adopters. The companies with more sophisticated pricing are able to drive adverse selection by stealing the good risks and leaving the poor risks behind for their competition.


So when is the best time to implement predictive analytics? There’s no time like the present. Carriers today are using advanced data and analytics to gain an advantage, and the number of carriers armed with this kind of insight is increasing in a big way. This is a battlefield in which superior information defines the high ground. Those with access to this information can maintain their strategic position – defending their place on good risks and refusing to take on new bad risks. Those without it can’t.

It’s time to take the first step. Here’s how.


“You never change things by fighting the existing reality.
To change something, build a new model that makes the existing model obsolete.”
–R. Buckminster Fuller


Bret Shroyer, FCAS, is an actuary and VP of Services for Valen Analytics. He serves as an advocate for Valen’s clients, bridging the gap that sometimes grows between technical modeling and client service teams, executives, actuaries, and underwriters. He helps the models drive success stories as they translate how data analytics helps people make better decisions and deliver tangible results.

Bret joined Valen in 2014 after serving as SVP of Reinsurance at Willis Re for five years. From 2006 to 2008, Bret served as CFO of an environmental consulting and construction firm. Immediately prior to this, Bret held numerous positions including Senior Actuary, Underwriting Director, and Predictive Modeling Manager during his ten-year tenure at Travelers.

Bret earned a B.A. in Mathematics from the University of St. Thomas in St. Paul, Minnesota, and is a Fellow of the Casualty Actuarial Society.