Next-Level Commercial Underwriting: Adaptive Analytics for Real-Time Decisions

To move from reactive to proactive underwriting, carriers must deploy dynamic strategies that combine predictive analytics with adaptive decisioning capabilities that change underwriting strategies in real time.

As carriers today are relying less on investment returns as a primary source of profitability, they are realizing the mountains of data they already “own” can serve as a strong source for increased profits. This holds especially true in how carriers can make better underwriting decisions based on the data and metrics that drive risk adjusted profitability. While the industry has been actively investing in modern data strategies, the results so far have been mixed, with many still searching for ways to monetize those investments. It’s those carriers that leverage systems such as predictive and adaptive analytics to make more strategic underwriting decisions that are poised to be market disruptors.

So how do carriers maximize their use of data so they can align both distribution channels and underwriting functions to become more profitable? It starts by becoming proactive. Suggesting the right offer, providing alternative product suggestions, coaching on risk appetite or new product offerings are all key. In short, this is about providing underwriters with tools to educate the channel on how they can best use their products and services.

Data – and analytics leveraging that data – can help carriers turn the tide by aligning underwriting decisions directly to the metrics that define performance. Many carriers are already using some form of analytics to help them score risks. However, that approach can be amped up to help insurers optimize multiple touch points across the underwriting process.

Traditional Approach: Retrospective

The current approach to leveraging analytics is like driving by mainly using your rear-view mirror – it tends to be more retrospective and lagging in nature. While predictive models are invaluable tools, they lack real-time qualities and tend largely impact strategy after the fact. While a leading indicator can and does play a valuable role in the underwriting process, what happens when the book of business has materially changed and the relevance of that indicator has changed?

New Approach: Dynamically Adaptive

In order to up their game, carriers need to look at how to start applying those analytics in a proactive, dynamic way. By combining predictive analytics with adaptive analytics, carriers can not only understand and interpret the characteristics of a risk; they can also start to make that information actionable. They can do this by deploying dynamic underwriting strategies that combine the predictive knowledge that analytics can provide with adaptive decisioning strategies that adapt and change underwriting strategies in real time. As carriers begin to make decisions that impact the total profitability of the business, they can change and adapt those strategies based on the real-time composition of the business.

Let’s take an illustrative example of how commercial lines carriers can embed robust, data-driven decisioning strategies within the underwriting process – and align them directly to business objectives.

Instead of the typical ‘first in, first out’ model that many commercial carriers use when a submission is received, they can now move toward one that is dynamic and continuously prioritize which risks underwriters should be working on first. Commercial carriers can use predictive analytics to score value across multiple inputs and begin to identify:

  • What products might be the best fit for the customer based on products that are a focus for your organization today;
  • How attractive the risk is to your bottom line and whether it fits with objectives for deploying underwriting capacity;
  • The risk/reward of each submission and impact it has on short/long-term profitability;
  • And factor in how customer/producer relationships may influence the decisions you make based on their value to your business.

Once you’ve scored and ranked things with predictive intelligence, adaptive analytics can take over and can drive decisions and strategies on what to do next. Adaptive analytics enable you to move your models as data inputs change (rather than deploy a static model that needs to be updated every three months or year – is always looking at the data). They can be used to change the strategy that a carrier might choose to take for this risk.

Adaptive analytics let you address pertinent questions including:

Should this hit the top of the pile first? Are we optimizing products based on the characteristic of the risk? Is this a good risk for our portfolio – and current profitability position? Are there external factors, like a top performing producer or segment of focus, at play that will impact how much we sharpen the pencil for this risk?

The result of these efforts: You can proactively drive better underwriting decisions and tailor the best strategy for each risk, and combine it with the best approach for your business.

Tom Harrington // Tom Harrington supports Pega’s global strategy for the insurance market and has more than 20 years of insurance industry experience. He works with leading carriers on innovation, profitable growth, digital transformation and policyholder engagement initiatives. Prior to joining Pegasystems, Harrington led product development, distribution strategy and technology initiatives at Liberty Mutual, and was a commercial lines insurance broker at Aon.  

Comment (1)

  1. Tom — Previously had not seen the usage of “adaptive analytics”. Really like the concept of blending that with the predictive analytics to illustrate the usage of the two.

Leave a Comment