The Data Challenge
How custom segmentation helps The San Diego Union-Tribune find new subscribers
Like at all major newspapers, it has become harder and more costly for The San Diego Union-Tribune—the second-largest newspaper in Southern California—to find new subscribers. To develop marketing and sales plans to approach consumers differently based on their lifestyle and circulation habits, the marketing and circulation team at the Union-Tribune determined it needed to develop a custom segmentation system.
Two recent business changes helped propel the marketing and circulation team’s challenges. The first change was internal: The Union-Tribune recently started to promote four-day and Sunday-only subscriptions; previously only seven-day subscriptions had been pitched actively. While the new offers were successful in acquiring more four-day and Sunday subscribers, some of its acquisition efforts were achieved at the expense of seven-day subscriptions it might have sold. Realizing this, the Union-Tribune wanted to identify prospects most likely to sign up for the different types of subscriptions and approach them with the right offer.
The second big impact to new customer acquisition was external: the Do-Not-Call Registry, which took effect in the fall of 2003. Like most newspapers, the Union-Tribune relied on telemarketing for the largest percentage of subscription starts. To offset the impact of a do-not-call list, the Union-Tribune needed to identify best prospects for other direct response acquisition channels such as direct mail and door-to-door canvassing.
To leverage its investment in Claritas data metrics, the Union-Tribune partnered with Integras, the analytical services division of Claritas Inc., to build a custom segmentation system.
A needs assessment determined the newspaper’s custom segmentation system would require a hierarchical framework that could be used for different applications. Strategically, it was important the system have a small and manageable number of consumer segments that could be used for messaging and positioning. For more tactical day-to-day applications such as acquisition, retention, upsell and re-activation, a larger number of more discrete segments would be needed.
When designing the custom segmentation system, levels needed to be built in that could be reclustered or collapsed into a small number of segments. The Union-Tribune needed a system that would “roll up and down” to these different levels to provide consistency across the organization.
Integras worked with the Union-Tribune to understand its goals and objectives; the data inputs required by these goals; and its budget, resources and implementation requirements. It was important that the segmentation system be able to serve the needs of multiple departments that handled various applications: acquisition, retention, cross-sell, churn, response, etc. The segmentation system, thus, would need to predict multiple behaviors. Typically, the more behaviors a company incorporates into a custom segmentation system, the more the resulting system gives up in terms of predicting any one behavior. It’s always a trade-off.
On the upside, when multiple behaviors are considered together, the model creates segments that have greater meaning across a wider range of departments and applications. On the downside, the system creates segments with less differentiation for any one given behavior.
Careful consideration was given to these pros and cons, and it was determined that the corporate-wide integration advantages would outweigh the loss of discrimination that might come with building one-off models for each application/department.
Building the System
The Union-Tribune provided Integras with data from three sources: an internal household-level customer file; a proprietary readership study; and the local do-not-call list. The customer file was instrumental in providing key information to create the custom segments.
By extrapolating data from the customer file, Integras identified a number of key consumer behaviors including how much a consumer paid for a subscription, length of the subscription, length of time on the file, etc. It was this type of behavioral data that was used to drive and create the custom segments. The attitudinal and needs-based data—derived from readership surveys—were used to tailor the custom segment descriptions. The goal was to define segments that behave similarly and then understand messaging insights that would evoke those behaviors.
Once the segments were defined using circulation behavior, data from the Union-Tribune’s proprietary readership study and the local do-not-call list were appended to the file to help define and localize the segments. Because both data sources lacked addresses, address records were reverse-appended to the telephone numbers using a unique cross-reference directory. Once the three data sources had addresses, they were combined into one file for analysis.
The proprietary readership study provided a wealth of information and helped to localize the segments to the San Diego market. This study provided information on daily versus Sunday readership, section readership, purchasing habits and topics of interest.
The local do-not-call list was obtained from www.donotcall.gov. The recent change in telemarketing legislation made it imperative that the Union-Tribune identify which consumer segments were most and least likely to be on the Do-Not-Call Registry.
Taking the three data sets provided by the the newspaper, Integras conducted a data audit—a critical step for companies with traditional operational customer files (files focused on billing versus marketing analysis). This process enabled Integras to validate the information provided by the newspaper and to interpret internal codes. The data audit revealed data anomalies such as zero values, missing fields, problem source codes and outliers.
Once all of the information was validated and corrected for analysis—which required several weeks of interaction between Integras and the Union-Tribune’s IT department (and multiple data pulls to correct for data integrity issues)—more than 300 behavioral profiles were created using factor analysis and clustering techniques. The resulting system yielded six final segments that were both meaningful and relevant in terms of multiple behaviors.
These six segments range from Segment No. 1, which represents a customer who pays full rate for his or her subscription and has subscribed for more than three years, to Segment No. 6, which represents subscribers who tend only to purchase the newspaper at a discount and stop subscribing once the discount expires.
The custom system was built using two levels. At a strategic level, Integras developed six custom segments from which the Union-Tribune could develop special messaging and positioning strategies. At a tactical level, the six custom segments map to 66 sub-segments that the Union-Tribune can use for targeting campaigns.
The Initial Results
The Union-Tribune has an internal database marketing and circulation sales team that holds ongoing meetings to develop direct response strategies and tactics. The foundation for these plans are the custom segments. Now that the custom segments are in-house, its first step will be to run test direct response programs to validate the six segments. The Union-Tribune plans to focus on an intensive direct response campaign for circulation acquisition, upgrades and reactivation.
Moving forward, the Union-Tribune plans to use these segments to:
• pull direct response mail lists that look like best customers;
• determine the right product offer and price;
• develop appealing copy and creative executions;
• assess how to best approach different consumers—i.e., telephone solicitation, door-to-door, direct mail; and
• develop appropriate retention tools.
Armed with better marketing insight, the Union-Tribune expects to greatly improve the effectiveness and profitability of its acquisition efforts.
Ramona Cyr is the group research manager at The San Diego Union-Tribune. Cyr can be reached at email@example.com. Jim Laiderman is vice president of customer targeting and segmentation at Integras, a division of Claritas Inc. Laiderman can be reached at firstname.lastname@example.org