When carriers who are having profitability problems for a segment of business attempt to correct the issue, they all too often go about it the wrong way. These are the steps we see on a very regular basis:
- Put in place a 10% rate increase. (After which loss ratio actually deteriorates.)
- Find a poor-performing class or region and exit that business. (Volume drops, but results don’t materially improve.)
- Resort to predictive analytics to find an answer.
In reality, these efforts should have started with the third step above and moved forward from there. Beginning with predictive analytics, the carrier can identify the policies or groups of policies that are performing better or worse than expected. This almost never results in the conclusion that barbers (sorry, I had to pick on someone) should be non-renewed, or that the carrier simply needs to stop writing in Allenstown. Instead, it points to the policies in each of those groups that are predicted to be trouble as well as identifies the policies in those groups that are predicted to be profitable.
Farm Bureau Financial Services, which writes workers compensation coverage, is one of the exceptions to this rule. In 2012, they were in some trouble so they quickly implemented predictive analytics into their BOP commercial lines to improve underwriting profitability and turn the ship around. As a result, they not only reduced their loss ratio by 66% from 2012 to 2014, they also grew their premium by 22.4% in 2013 and 10.1% in 2014.
As Farm Bureau learned, there’s something surprising that happens when you start looking at predictive statistics on an in-force book. The model doesn’t have pre-conceived notions about which regions or classes are in or out of favor. As a result, within the worst-performing class, the model might find that 25% of the policies are significantly better than average, and should be retained. Conversely, within the best-performing class, the model might find that 25% are significantly worse than average, and should be cut.
This is how carriers experience significant wins when implementing predictive analytics for the first time. They discover many opportunities to make significant improvements in risk selection and pricing on the in-force book, and for the first time they can actually see and measure the impact of adverse selection on their book in recent years. There are so many opportunities to gather this low hanging fruit that it’s hard to choose a bad place to start once you have a reliable model in place.
As a result, the preferred order of operations becomes:
- Implement predictive analytics to look at prospective profitability at the policy level.
- Use that information to drive risk selection and pricing at the policy level. This will result in non-renewing or losing some segments, and growing other segments. These segments emerge organically, from the bottom up, rather than as a general strategy from the top down.
- After re-underwriting and re-pricing the book, adjust base rate level for portfolio profitability target.
The final result is a portfolio comprising risks that you want to write, at adequate prices. It may even include some Allenstown barbers.
ABOUT THE AUTHOR:
Bret Shroyer, FCAS, is an actuary and Solutions Architect 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.