
Let MiLo find the right audience for you.
ROI Solutions’ machine learning platform, named MiLo™, can create custom models for client organizations across the constituent lifecycle. MiLo uses client data to score a constituent audience based on the predicted likelihood of response. MiLo has the capability to run literally billions of data iterations and interactions across hundreds of time-tested machine learning algorithms to find the client-specific data that is predictive and the one model that will perform best for your organization.
MiLo allows ROI Solutions to do two things very efficiently: find the best model for the use case to optimize audience selection and continually learn from the results to fine tune the models. Over the last few years we have partnered with select clients to build, test, and refine models for Lapsed Recapture, Sustainer Loyalty, and Premium vs. Non-Premium. Unlike typical Coop-driven models, MiLo uses clients’ data from their own CRM This data can include transactional information, contact history, other interactions with the organization, and even appended demographic data. Our clients do not have to share their constituent information with a Coop and each model that we deliver is client-specific because each client (and the data that is found to be predictive) is unique.

- Model scores can reside within your organization’s CRM to easily target audiences across marketing channels
- Models utilize client-specific data and can include third-party demographic overlay data
- Custom model builds for desired outcomes
- Existing models include Lapsed Recapture, Sustainer Loyalty, and Premium Responsiveness
Case Study: Human Rights Campaign
Lapsed & Deep Lapsed Recapture Model
The Challenge
Human Rights Campaign (HRC) had been using a variety of internally developed and vendor-sourced models with varying results. At the start of the pandemic, they knew they had to try something new to recapture more lapsed donors.
The Model Build
The MiLo Team worked with HRC to determine typical audiences for existing lapsed recapture efforts, the contact cadence, and curated both giving and response data as well as other engagement variables to create a robust model that was able to extend the outreach of HRC to a far deeper lapsed audience.
The Model Build
The Lapsed and Deep Lapsed Model was tested against several internal and Coop models and performed extremely well. Response rate increased 41% while at the same time mail volume increased over 38% compared to prior efforts. The net result was a 95% revenue lift for HRC on their annual lapsed recapture program. HRC has rolled out with this model to replace their previous models and scores are refreshed with every new campaign.

95% Revenue Lift
The HRC Lapsed and Deep Lapsed model uncovered some donors that the organization had not typically included in their lapsed recapture marketing programs. In fact, some of these donors had not been active in over 20 years!
Do you need help optimizing your campaign audience?
Let’s discuss how MiLo can help your organization find and target the right audience to make the most of your creative campaigns.