Case Studies

Battling List Fatigue? Major, privately-funded non-profit organization battles list fatigue

In the non-profit world, soliciting for charitable donations is extremely competitive, which makes it difficult to identify new donors and increase the average gift amount. Non-profit organizations rely heavily on list exchanges for their direct marketing campaigns, so it's challenging to find new prospects that are not already on existing lists. For national organizations, identifying new donors is especially crucial to fundraising efforts. When a major, national non-profit was struggling with list fatigue, it looked to us to help it identify new sources of names not yet exhausted by previous campaigns.

Creating Custom Models

Applying genetic algorithms to predictive modeling creates targeted prospect universes that are customized for every campaign. By applying over 750 variables to data on more than 120 million households, we are able to generate models that are scored to produce highly-targeted mailing lists that can improve response rates by 7.5-15%.

Non-profits operate on an extremely tight budget; they must maximize their marketing dollars and cut costs wherever possible. This organization was looking to locate new donors while minimizing direct marketing costs and increasing the donor base. Profiles were created of existing donors from successful campaigns, enabling the non-profit to see the nationwide demographic and geographic attributes associated with its customer base. Once the existing donor base was revealed, we were able to build custom, predictive models to help identify the strongest traits among groups nationwide so new prospects could be identified quickly and easily. A custom prospect universe was created for the organization that it could use for its current campaign, and for future mailings as well.

The Results

By identifying the demographic and geographic variables in successful campaigns, we were able to locate new prospects that were not on any of the organization's previous mail lists. The custom models identified the "most likely" new donors nationwide, and the data analysis revealed new segments to target. The resultant campaign yielded higher response rates and better donor acquisition numbers than previous mailings; in the first four months of the campaign, the organization received over $150,000 in new acquisition dollars. Furthermore, it was able to save costs by mailing to these "replacement names" who were likely to respond, rather than repeat names on its original lists who were not.

Go Back