Getting the price right

At RSA Canada, getting the premium right is the difference between profitable risk and unprofitable risk

“There’s no such thing as a bad risk, as long as you’ve got the premium right,” says Kathy Kim, Director of Actuarial Systems for insurance company RSA Canada.

Getting the premium right is what RSA Canada’s actuarial department does. The 60 actuarial staff members – 50 in Ontario and 10 in Quebec – serve the six RSA Canada group insurance companies by using advanced analytics to ensure the profitability of its $3 billion annual portfolio of premiums.

SAS helps us increase the accuracy of our pricing models.

Kathy Kim
Director of Actuarial Systems

With data coming from four different systems on four different platforms, the information technology department combines the data from those systems – more than five terabytes – into a single view. It’s then fed into the company’s SAS® server so the actuarial department can build the premium rating models.

One function of this is rate filings – any insurance company in Ontario has to justify rate increases to the government. “Let’s say I have a two-vehicle family with one underage driver,” says Kim. “If I’m going to charge different rates for different risk characteristics, what’s the effect on the total premium if I am to change my pricing model?”

Using SAS and its generalized linear modeling capabilities enables RSA Canada to re-rate and forecast how these rate changes affect its book of business.

“SAS is used in all aspects of rating model construction,” says Kim. “It is used for cleaning and analysis of data used for building predictive models, manipulating these models for business implementation and monitoring the implementation results. SAS is also heavily used in our dynamic portfolio monitoring, such as decile analysis.

“The main benefit of SAS is to come up with a rating model that will tell us the actual cost of doing business or profitability for certain segments and certain risk groups. You want to price in such a way that it’s giving you 10 percent or 15 percent return. SAS helps us increase the accuracy of our pricing models.”

And SAS gives RSA Canada the ability to easily add new risk factors. For example, in 2013 there was a spike in weather-related insurance claims. Based on existing available data, RSA Canada can adjust premiums for areas with higher risks of water damage.

But it’s not just about risk profiles and premiums. “Lately, we’ve been doing a lot of segmentation studies,” Kim says. RSA Canada uses advanced analytics to identify highly profitable market segments the company wants to grow – and, conversely, less-profitable segments the company should be shrinking.

Another reason Kim is excited about the company’s migration to a server with SAS 9.4 is the SAS Visual Analytics solution. To do such segmentation analysis now requires coding, but SAS Visual Analytics enables segmentation through a simple graphical interface.

“Right now, if we want to see the premium distribution by different regions in Ontario, we have to write a program to summarize our data,” Kim says. “But SAS Visual Analytics can now do that automatically without writing code.”

SAS also offers Kim better monitoring and management of how SAS IT resources are used.

“It wasn’t a big issue before because we had only a handful of people who were using SAS,” Kim says. But the department has doubled in size over the last two years, and the number of SAS users tripled. With 10 to 20 users on SAS at any given time, tracking down resource hogs and ensuring quality of service for high-priority jobs was a challenge.

“With this new SAS solution, we should be able to quickly monitor IT resources, and if there’s any urgent job that has to run, we can identify which job is causing a bottleneck,” Kim says.

RSA Canada is in the process of standardizing the disparate platforms on an enterprise data warehouse. This will allow the company to eliminate much of the data preparation workload and access information directly through SAS Visual Analytics.

RSA Logo


Accurately predict the impact of risk characteristics on customer premiums, while identifying customer segments with growth potential.


SAS® Visual Analytics
SAS® Office Analytics


Ensuring profitability and compliance while identifying growth segments.

About the customer

RSA Canada – including Royal & Sun Alliance Insurance Company of Canada, Unifund Assurance Company, Canadian Northern Shield Insurance Company, Western Assurance Company, Quebec Assurance Company and Ascentus Insurance Ltd. – offers property, automotive, small business, travel, pet and large commercial insurance accounts. Property and automotive insurance make up a little more than half the company’s book.

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.