Wiland Announces Powerful New Models to Increase Acquisition Volume
Niwot, CO – July 9, 2018 – Wiland, Inc., a leading provider of marketing audiences, marketing optimization, and business intelligence, has announced the creation of three new modeling solutions that deliver high-performance, high-volume audiences for online and offline acquisition campaigns.
By combining Wiland’s machine learning platform and advanced elastic net modeling techniques, these solutions mathematically leverage more transactional information and more variables to identify unique pockets of prospect names for clients, resulting in increased, high-quality volume for their acquisition campaigns.
“Wiland continues to push the limits of predictive modeling,” says Tom Murray, President of Wiland’s Cooperative Database Division. “These new models represent another step forward in providing clients with the best possible audiences that will improve campaign success and produce superior ROI.”
Among the new solutions being introduced by Wiland are two enhanced profile models that amplify the strength of existing profile solutions and rival Wiland’s highly-regarded response models. Wiland has also developed an entirely new response model leveraging elastic net methodologies. Each of these new models is available to Wiland clients for incremental growth, standalone usage, or as input in a multi-model Universal Performance solution.
- Enhanced Best Customer/Donor Model
Draws from the vast data of the Wiland Cooperative Database to identify names most closely correlated to the client’s highest value customers/donors, pinpointing prospects with the highest likelihood of engagement.
- Enhanced List Affinity Model
Analyzes hundreds of predictive data variables to identify prospects from lists highly correlated to the client’s list based on offer, creative presentation, and statistically observed synergy with the client’s customer/donor base.
- New! Elastic Net Response Model
Evaluates and weights hundreds of variables to create an optimal mix of key predictors to find ideal prospects often missed by traditional regression models.
To learn more about these exciting new modeling solutions, interested parties can reach out to firstname.lastname@example.org.